-
Improved Algorithm and Bounds for Successive Projection
Authors:
Jiashun Jin,
Zheng Tracy Ke,
Gabriel Moryoussef,
Jiajun Tang,
Jingming Wang
Abstract:
Given a $K$-vertex simplex in a $d$-dimensional space, suppose we measure $n$ points on the simplex with noise (hence, some of the observed points fall outside the simplex). Vertex hunting is the problem of estimating the $K$ vertices of the simplex. A popular vertex hunting algorithm is successive projection algorithm (SPA). However, SPA is observed to perform unsatisfactorily under strong noise…
▽ More
Given a $K$-vertex simplex in a $d$-dimensional space, suppose we measure $n$ points on the simplex with noise (hence, some of the observed points fall outside the simplex). Vertex hunting is the problem of estimating the $K$ vertices of the simplex. A popular vertex hunting algorithm is successive projection algorithm (SPA). However, SPA is observed to perform unsatisfactorily under strong noise or outliers. We propose pseudo-point SPA (pp-SPA). It uses a projection step and a denoise step to generate pseudo-points and feed them into SPA for vertex hunting. We derive error bounds for pp-SPA, leveraging on extreme value theory of (possibly) high-dimensional random vectors. The results suggest that pp-SPA has faster rates and better numerical performances than SPA. Our analysis includes an improved non-asymptotic bound for the original SPA, which is of independent interest.
△ Less
Submitted 16 March, 2024;
originally announced March 2024.
-
The Fallacy of Minimizing Local Regret in the Sequential Task Setting
Authors:
Ziping Xu,
Kelly W. Zhang,
Susan A. Murphy
Abstract:
In the realm of Reinforcement Learning (RL), online RL is often conceptualized as an optimization problem, where an algorithm interacts with an unknown environment to minimize cumulative regret. In a stationary setting, strong theoretical guarantees, like a sublinear ($\sqrt{T}$) regret bound, can be obtained, which typically implies the convergence to an optimal policy and the cessation of explor…
▽ More
In the realm of Reinforcement Learning (RL), online RL is often conceptualized as an optimization problem, where an algorithm interacts with an unknown environment to minimize cumulative regret. In a stationary setting, strong theoretical guarantees, like a sublinear ($\sqrt{T}$) regret bound, can be obtained, which typically implies the convergence to an optimal policy and the cessation of exploration. However, these theoretical setups often oversimplify the complexities encountered in real-world RL implementations, where tasks arrive sequentially with substantial changes between tasks and the algorithm may not be allowed to adaptively learn within certain tasks. We study the changes beyond the outcome distributions, encompassing changes in the reward designs (mappings from outcomes to rewards) and the permissible policy spaces. Our results reveal the fallacy of myopically minimizing regret within each task: obtaining optimal regret rates in the early tasks may lead to worse rates in the subsequent ones, even when the outcome distributions stay the same. To realize the optimal cumulative regret bound across all the tasks, the algorithm has to overly explore in the earlier tasks. This theoretical insight is practically significant, suggesting that due to unanticipated changes (e.g., rapid technological development or human-in-the-loop involvement) between tasks, the algorithm needs to explore more than it would in the usual stationary setting within each task. Such implication resonates with the common practice of using clipped policies in mobile health clinical trials and maintaining a fixed rate of $ε$-greedy exploration in robotic learning.
△ Less
Submitted 16 March, 2024;
originally announced March 2024.
-
Efficient Pruning of Large Language Model with Adaptive Estimation Fusion
Authors:
Jun Liu,
Chao Wu,
Changdi Yang,
Hao Tang,
Haoye Dong,
Zhenglun Kong,
Geng Yuan,
Wei Niu,
Dong Huang,
Yanzhi Wang
Abstract:
Large language models (LLMs) have become crucial for many generative downstream tasks, leading to an inevitable trend and significant challenge to deploy them efficiently on resource-constrained devices. Structured pruning is a widely used method to address this challenge. However, when dealing with the complex structure of the multiple decoder layers, general methods often employ common estimatio…
▽ More
Large language models (LLMs) have become crucial for many generative downstream tasks, leading to an inevitable trend and significant challenge to deploy them efficiently on resource-constrained devices. Structured pruning is a widely used method to address this challenge. However, when dealing with the complex structure of the multiple decoder layers, general methods often employ common estimation approaches for pruning. These approaches lead to a decline in accuracy for specific downstream tasks. In this paper, we introduce a simple yet efficient method that adaptively models the importance of each substructure. Meanwhile, it can adaptively fuse coarse-grained and finegrained estimations based on the results from complex and multilayer structures. All aspects of our design seamlessly integrate into the endto-end pruning framework. Our experimental results, compared with state-of-the-art methods on mainstream datasets, demonstrate average accuracy improvements of 1.1%, 1.02%, 2.0%, and 1.2% for LLaMa-7B,Vicuna-7B, Baichuan-7B, and Bloom-7b1, respectively.
△ Less
Submitted 16 March, 2024;
originally announced March 2024.
-
Enhancing Human-Centered Dynamic Scene Understanding via Multiple LLMs Collaborated Reasoning
Authors:
Hang Zhang,
Wenxiao Zhang,
Haoxuan Qu,
Jun Liu
Abstract:
Human-centered dynamic scene understanding plays a pivotal role in enhancing the capability of robotic and autonomous systems, in which Video-based Human-Object Interaction (V-HOI) detection is a crucial task in semantic scene understanding, aimed at comprehensively understanding HOI relationships within a video to benefit the behavioral decisions of mobile robots and autonomous driving systems. A…
▽ More
Human-centered dynamic scene understanding plays a pivotal role in enhancing the capability of robotic and autonomous systems, in which Video-based Human-Object Interaction (V-HOI) detection is a crucial task in semantic scene understanding, aimed at comprehensively understanding HOI relationships within a video to benefit the behavioral decisions of mobile robots and autonomous driving systems. Although previous V-HOI detection models have made significant strides in accurate detection on specific datasets, they still lack the general reasoning ability like human beings to effectively induce HOI relationships. In this study, we propose V-HOI Multi-LLMs Collaborated Reasoning (V-HOI MLCR), a novel framework consisting of a series of plug-and-play modules that could facilitate the performance of current V-HOI detection models by leveraging the strong reasoning ability of different off-the-shelf pre-trained large language models (LLMs). We design a two-stage collaboration system of different LLMs for the V-HOI task. Specifically, in the first stage, we design a Cross-Agents Reasoning scheme to leverage the LLM conduct reasoning from different aspects. In the second stage, we perform Multi-LLMs Debate to get the final reasoning answer based on the different knowledge in different LLMs. Additionally, we devise an auxiliary training strategy that utilizes CLIP, a large vision-language model to enhance the base V-HOI models' discriminative ability to better cooperate with LLMs. We validate the superiority of our design by demonstrating its effectiveness in improving the prediction accuracy of the base V-HOI model via reasoning from multiple perspectives.
△ Less
Submitted 15 March, 2024;
originally announced March 2024.
-
LyZNet: A Lightweight Python Tool for Learning and Verifying Neural Lyapunov Functions and Regions of Attraction
Authors:
Jun Liu,
Yiming Meng,
Maxwell Fitzsimmons,
Ruikun Zhou
Abstract:
In this paper, we describe a lightweight Python framework that provides integrated learning and verification of neural Lyapunov functions for stability analysis. The proposed tool, named LyZNet, learns neural Lyapunov functions using physics-informed neural networks (PINNs) to solve Zubov's equation and verifies them using satisfiability modulo theories (SMT) solvers. What distinguishes this tool…
▽ More
In this paper, we describe a lightweight Python framework that provides integrated learning and verification of neural Lyapunov functions for stability analysis. The proposed tool, named LyZNet, learns neural Lyapunov functions using physics-informed neural networks (PINNs) to solve Zubov's equation and verifies them using satisfiability modulo theories (SMT) solvers. What distinguishes this tool from others in the literature is its ability to provide verified regions of attraction close to the domain of attraction. This is achieved by encoding Zubov's partial differential equation (PDE) into the PINN approach. By embracing the non-convex nature of the underlying optimization problems, we demonstrate that in cases where convex optimization, such as semidefinite programming, fails to capture the domain of attraction, our neural network framework proves more successful. The tool also offers automatic decomposition of coupled nonlinear systems into a network of low-dimensional subsystems for compositional verification. We illustrate the tool's usage and effectiveness with several numerical examples, including both non-trivial low-dimensional nonlinear systems and high-dimensional systems. The repository of the tool can be found at https://git.uwaterloo.ca/hybrid-systems-lab/lyznet.
△ Less
Submitted 15 March, 2024;
originally announced March 2024.
-
A Semantic Mention Graph Augmented Model for Document-Level Event Argument Extraction
Authors:
Jian Zhang,
Changlin Yang,
Haiping Zhu,
Qika Lin,
Fangzhi Xu,
Jun Liu
Abstract:
Document-level Event Argument Extraction (DEAE) aims to identify arguments and their specific roles from an unstructured document. The advanced approaches on DEAE utilize prompt-based methods to guide pre-trained language models (PLMs) in extracting arguments from input documents. They mainly concentrate on establishing relations between triggers and entity mentions within documents, leaving two u…
▽ More
Document-level Event Argument Extraction (DEAE) aims to identify arguments and their specific roles from an unstructured document. The advanced approaches on DEAE utilize prompt-based methods to guide pre-trained language models (PLMs) in extracting arguments from input documents. They mainly concentrate on establishing relations between triggers and entity mentions within documents, leaving two unresolved problems: a) independent modeling of entity mentions; b) document-prompt isolation. To this end, we propose a semantic mention Graph Augmented Model (GAM) to address these two problems in this paper. Firstly, GAM constructs a semantic mention graph that captures relations within and between documents and prompts, encompassing co-existence, co-reference and co-type relations. Furthermore, we introduce an ensembled graph transformer module to address mentions and their three semantic relations effectively. Later, the graph-augmented encoder-decoder module incorporates the relation-specific graph into the input embedding of PLMs and optimizes the encoder section with topology information, enhancing the relations comprehensively. Extensive experiments on the RAMS and WikiEvents datasets demonstrate the effectiveness of our approach, surpassing baseline methods and achieving a new state-of-the-art performance.
△ Less
Submitted 12 March, 2024;
originally announced March 2024.
-
Towards Optimizing Human-Centric Objectives in AI-Assisted Decision-Making With Offline Reinforcement Learning
Authors:
Zana Buçinca,
Siddharth Swaroop,
Amanda E. Paluch,
Susan A. Murphy,
Krzysztof Z. Gajos
Abstract:
As AI assistance is increasingly infused into decision-making processes, we may seek to optimize human-centric objectives beyond decision accuracy, such as skill improvement or task enjoyment of individuals interacting with these systems. With this aspiration in mind, we propose offline reinforcement learning (RL) as a general approach for modeling human-AI decision-making to optimize such human-c…
▽ More
As AI assistance is increasingly infused into decision-making processes, we may seek to optimize human-centric objectives beyond decision accuracy, such as skill improvement or task enjoyment of individuals interacting with these systems. With this aspiration in mind, we propose offline reinforcement learning (RL) as a general approach for modeling human-AI decision-making to optimize such human-centric objectives. Our approach seeks to optimize different objectives by adaptively providing decision support to humans -- the right type of assistance, to the right person, at the right time. We instantiate our approach with two objectives: human-AI accuracy on the decision-making task and human learning about the task, and learn policies that optimize these two objectives from previous human-AI interaction data. We compare the optimized policies against various baselines in AI-assisted decision-making. Across two experiments (N = 316 and N = 964), our results consistently demonstrate that people interacting with policies optimized for accuracy achieve significantly better accuracy -- and even human-AI complementarity -- compared to those interacting with any other type of AI support. Our results further indicate that human learning is more difficult to optimize than accuracy, with participants who interacted with learning-optimized policies showing significant learning improvement only at times. Our research (1) demonstrates offline RL to be a promising approach to model dynamics of human-AI decision-making, leading to policies that may optimize various human-centric objectives and provide novel insights about the AI-assisted decision-making space, and (2) emphasizes the importance of considering human-centric objectives beyond decision accuracy in AI-assisted decision-making, while also opening up the novel research challenge of optimizing such objectives.
△ Less
Submitted 9 March, 2024;
originally announced March 2024.
-
LTGC: Long-tail Recognition via Leveraging LLMs-driven Generated Content
Authors:
Qihao Zhao,
Yalun Dai,
Hao Li,
Wei Hu,
Fan Zhang,
Jun Liu
Abstract:
Long-tail recognition is challenging because it requires the model to learn good representations from tail categories and address imbalances across all categories. In this paper, we propose a novel generative and fine-tuning framework, LTGC, to handle long-tail recognition via leveraging generated content. Firstly, inspired by the rich implicit knowledge in large-scale models (e.g., large language…
▽ More
Long-tail recognition is challenging because it requires the model to learn good representations from tail categories and address imbalances across all categories. In this paper, we propose a novel generative and fine-tuning framework, LTGC, to handle long-tail recognition via leveraging generated content. Firstly, inspired by the rich implicit knowledge in large-scale models (e.g., large language models, LLMs), LTGC leverages the power of these models to parse and reason over the original tail data to produce diverse tail-class content. We then propose several novel designs for LTGC to ensure the quality of the generated data and to efficiently fine-tune the model using both the generated and original data. The visualization demonstrates the effectiveness of the generation module in LTGC, which produces accurate and diverse tail data. Additionally, the experimental results demonstrate that our LTGC outperforms existing state-of-the-art methods on popular long-tailed benchmarks.
△ Less
Submitted 13 March, 2024; v1 submitted 9 March, 2024;
originally announced March 2024.
-
InstructGIE: Towards Generalizable Image Editing
Authors:
Zichong Meng,
Changdi Yang,
Jun Liu,
Hao Tang,
Pu Zhao,
Yanzhi Wang
Abstract:
Recent advances in image editing have been driven by the development of denoising diffusion models, marking a significant leap forward in this field. Despite these advances, the generalization capabilities of recent image editing approaches remain constrained. In response to this challenge, our study introduces a novel image editing framework with enhanced generalization robustness by boosting in-…
▽ More
Recent advances in image editing have been driven by the development of denoising diffusion models, marking a significant leap forward in this field. Despite these advances, the generalization capabilities of recent image editing approaches remain constrained. In response to this challenge, our study introduces a novel image editing framework with enhanced generalization robustness by boosting in-context learning capability and unifying language instruction. This framework incorporates a module specifically optimized for image editing tasks, leveraging the VMamba Block and an editing-shift matching strategy to augment in-context learning. Furthermore, we unveil a selective area-matching technique specifically engineered to address and rectify corrupted details in generated images, such as human facial features, to further improve the quality. Another key innovation of our approach is the integration of a language unification technique, which aligns language embeddings with editing semantics to elevate the quality of image editing. Moreover, we compile the first dataset for image editing with visual prompts and editing instructions that could be used to enhance in-context capability. Trained on this dataset, our methodology not only achieves superior synthesis quality for trained tasks, but also demonstrates robust generalization capability across unseen vision tasks through tailored prompts.
△ Less
Submitted 7 March, 2024;
originally announced March 2024.
-
IBD: Alleviating Hallucinations in Large Vision-Language Models via Image-Biased Decoding
Authors:
Lanyun Zhu,
Deyi Ji,
Tianrun Chen,
Peng Xu,
Jieping Ye,
Jun Liu
Abstract:
Despite achieving rapid developments and with widespread applications, Large Vision-Language Models (LVLMs) confront a serious challenge of being prone to generating hallucinations. An over-reliance on linguistic priors has been identified as a key factor leading to these hallucinations. In this paper, we propose to alleviate this problem by introducing a novel image-biased decoding (IBD) techniqu…
▽ More
Despite achieving rapid developments and with widespread applications, Large Vision-Language Models (LVLMs) confront a serious challenge of being prone to generating hallucinations. An over-reliance on linguistic priors has been identified as a key factor leading to these hallucinations. In this paper, we propose to alleviate this problem by introducing a novel image-biased decoding (IBD) technique. Our method derives the next-token probability distribution by contrasting predictions from a conventional LVLM with those of an image-biased LVLM, thereby amplifying the correct information highly correlated with image content while mitigating the hallucinatory errors caused by excessive dependence on text. We further conduct a comprehensive statistical analysis to validate the reliability of our method, and design an adaptive adjustment strategy to achieve robust and flexible handling under varying conditions. Experimental results across multiple evaluation metrics verify that our method, despite not requiring additional training data and only with a minimal increase in model parameters, can significantly reduce hallucinations in LVLMs and enhance the truthfulness of the generated response.
△ Less
Submitted 28 February, 2024;
originally announced February 2024.
-
reBandit: Random Effects based Online RL algorithm for Reducing Cannabis Use
Authors:
Susobhan Ghosh,
Yongyi Guo,
Pei-Yao Hung,
Lara Coughlin,
Erin Bonar,
Inbal Nahum-Shani,
Maureen Walton,
Susan Murphy
Abstract:
The escalating prevalence of cannabis use, and associated cannabis-use disorder (CUD), poses a significant public health challenge globally. With a notably wide treatment gap, especially among emerging adults (EAs; ages 18-25), addressing cannabis use and CUD remains a pivotal objective within the 2030 United Nations Agenda for Sustainable Development Goals (SDG). In this work, we develop an onlin…
▽ More
The escalating prevalence of cannabis use, and associated cannabis-use disorder (CUD), poses a significant public health challenge globally. With a notably wide treatment gap, especially among emerging adults (EAs; ages 18-25), addressing cannabis use and CUD remains a pivotal objective within the 2030 United Nations Agenda for Sustainable Development Goals (SDG). In this work, we develop an online reinforcement learning (RL) algorithm called reBandit which will be utilized in a mobile health study to deliver personalized mobile health interventions aimed at reducing cannabis use among EAs. reBandit utilizes random effects and informative Bayesian priors to learn quickly and efficiently in noisy mobile health environments. Moreover, reBandit employs Empirical Bayes and optimization techniques to autonomously update its hyper-parameters online. To evaluate the performance of our algorithm, we construct a simulation testbed using data from a prior study, and compare against commonly used algorithms in mobile health studies. We show that reBandit performs equally well or better than all the baseline algorithms, and the performance gap widens as population heterogeneity increases in the simulation environment, proving its adeptness to adapt to diverse population of study participants.
△ Less
Submitted 27 February, 2024;
originally announced February 2024.
-
Monitoring Fidelity of Online Reinforcement Learning Algorithms in Clinical Trials
Authors:
Anna L. Trella,
Kelly W. Zhang,
Inbal Nahum-Shani,
Vivek Shetty,
Iris Yan,
Finale Doshi-Velez,
Susan A. Murphy
Abstract:
Online reinforcement learning (RL) algorithms offer great potential for personalizing treatment for participants in clinical trials. However, deploying an online, autonomous algorithm in the high-stakes healthcare setting makes quality control and data quality especially difficult to achieve. This paper proposes algorithm fidelity as a critical requirement for deploying online RL algorithms in cli…
▽ More
Online reinforcement learning (RL) algorithms offer great potential for personalizing treatment for participants in clinical trials. However, deploying an online, autonomous algorithm in the high-stakes healthcare setting makes quality control and data quality especially difficult to achieve. This paper proposes algorithm fidelity as a critical requirement for deploying online RL algorithms in clinical trials. It emphasizes the responsibility of the algorithm to (1) safeguard participants and (2) preserve the scientific utility of the data for post-trial analyses. We also present a framework for pre-deployment planning and real-time monitoring to help algorithm developers and clinical researchers ensure algorithm fidelity. To illustrate our framework's practical application, we present real-world examples from the Oralytics clinical trial. Since Spring 2023, this trial successfully deployed an autonomous, online RL algorithm to personalize behavioral interventions for participants at risk for dental disease.
△ Less
Submitted 26 February, 2024;
originally announced February 2024.
-
An inexact Bregman proximal point method and its acceleration version for unbalanced optimal transport
Authors:
Xiang Chen,
Faqiang Wang,
Jun Liu,
Li Cui
Abstract:
The Unbalanced Optimal Transport (UOT) problem plays increasingly important roles in computational biology, computational imaging and deep learning. Scaling algorithm is widely used to solve UOT due to its convenience and good convergence properties. However, this algorithm has lower accuracy for large regularization parameters, and due to stability issues, small regularization parameters can easi…
▽ More
The Unbalanced Optimal Transport (UOT) problem plays increasingly important roles in computational biology, computational imaging and deep learning. Scaling algorithm is widely used to solve UOT due to its convenience and good convergence properties. However, this algorithm has lower accuracy for large regularization parameters, and due to stability issues, small regularization parameters can easily lead to numerical overflow. We address this challenge by developing an inexact Bregman proximal point method for solving UOT. This algorithm approximates the proximal operator using the Scaling algorithm at each iteration. The algorithm (1) converges to the true solution of UOT, (2) has theoretical guarantees and robust regularization parameter selection, (3) mitigates numerical stability issues, and (4) can achieve comparable computational complexity to the Scaling algorithm in specific practice. Building upon this, we develop an accelerated version of inexact Bregman proximal point method for solving UOT by using acceleration techniques of Bregman proximal point method and provide theoretical guarantees and experimental validation of convergence and acceleration.
△ Less
Submitted 26 February, 2024;
originally announced February 2024.
-
Evaluating the Effectiveness of Index-Based Treatment Allocation
Authors:
Niclas Boehmer,
Yash Nair,
Sanket Shah,
Lucas Janson,
Aparna Taneja,
Milind Tambe
Abstract:
When resources are scarce, an allocation policy is needed to decide who receives a resource. This problem occurs, for instance, when allocating scarce medical resources and is often solved using modern ML methods. This paper introduces methods to evaluate index-based allocation policies -- that allocate a fixed number of resources to those who need them the most -- by using data from a randomized…
▽ More
When resources are scarce, an allocation policy is needed to decide who receives a resource. This problem occurs, for instance, when allocating scarce medical resources and is often solved using modern ML methods. This paper introduces methods to evaluate index-based allocation policies -- that allocate a fixed number of resources to those who need them the most -- by using data from a randomized control trial. Such policies create dependencies between agents, which render the assumptions behind standard statistical tests invalid and limit the effectiveness of estimators. Addressing these challenges, we translate and extend recent ideas from the statistics literature to present an efficient estimator and methods for computing asymptotically correct confidence intervals. This enables us to effectively draw valid statistical conclusions, a critical gap in previous work. Our extensive experiments validate our methodology in practical settings, while also showcasing its statistical power. We conclude by proposing and empirically verifying extensions of our methodology that enable us to reevaluate a past randomized control trial to evaluate different ML allocation policies in the context of a mHealth program, drawing previously invisible conclusions.
△ Less
Submitted 18 February, 2024;
originally announced February 2024.
-
Denoising Diffusion Restoration Tackles Forward and Inverse Problems for the Laplace Operator
Authors:
Amartya Mukherjee,
Melissa M. Stadt,
Lena Podina,
Mohammad Kohandel,
Jun Liu
Abstract:
Diffusion models have emerged as a promising class of generative models that map noisy inputs to realistic images. More recently, they have been employed to generate solutions to partial differential equations (PDEs). However, they still struggle with inverse problems in the Laplacian operator, for instance, the Poisson equation, because the eigenvalues that are large in magnitude amplify the meas…
▽ More
Diffusion models have emerged as a promising class of generative models that map noisy inputs to realistic images. More recently, they have been employed to generate solutions to partial differential equations (PDEs). However, they still struggle with inverse problems in the Laplacian operator, for instance, the Poisson equation, because the eigenvalues that are large in magnitude amplify the measurement noise. This paper presents a novel approach for the inverse and forward solution of PDEs through the use of denoising diffusion restoration models (DDRM). DDRMs were used in linear inverse problems to restore original clean signals by exploiting the singular value decomposition (SVD) of the linear operator. Equivalently, we present an approach to restore the solution and the parameters in the Poisson equation by exploiting the eigenvalues and the eigenfunctions of the Laplacian operator. Our results show that using denoising diffusion restoration significantly improves the estimation of the solution and parameters. Our research, as a result, pioneers the integration of diffusion models with the principles of underlying physics to solve PDEs.
△ Less
Submitted 14 February, 2024; v1 submitted 13 February, 2024;
originally announced February 2024.
-
A Bayesian Approach to Online Learning for Contextual Restless Bandits with Applications to Public Health
Authors:
Biyonka Liang,
Lily Xu,
Aparna Taneja,
Milind Tambe,
Lucas Janson
Abstract:
Restless multi-armed bandits (RMABs) are used to model sequential resource allocation in public health intervention programs. In these settings, the underlying transition dynamics are often unknown a priori, requiring online reinforcement learning (RL). However, existing methods in online RL for RMABs cannot incorporate properties often present in real-world public health applications, such as con…
▽ More
Restless multi-armed bandits (RMABs) are used to model sequential resource allocation in public health intervention programs. In these settings, the underlying transition dynamics are often unknown a priori, requiring online reinforcement learning (RL). However, existing methods in online RL for RMABs cannot incorporate properties often present in real-world public health applications, such as contextual information and non-stationarity. We present Bayesian Learning for Contextual RMABs (BCoR), an online RL approach for RMABs that novelly combines techniques in Bayesian modeling with Thompson sampling to flexibly model a wide range of complex RMAB settings, such as contextual and non-stationary RMABs. A key contribution of our approach is its ability to leverage shared information within and between arms to learn unknown RMAB transition dynamics quickly in budget-constrained settings with relatively short time horizons. Empirically, we show that BCoR achieves substantially higher finite-sample performance than existing approaches over a range of experimental settings, including one constructed from a real-world public health campaign in India.
△ Less
Submitted 7 February, 2024;
originally announced February 2024.
-
Meet JEANIE: a Similarity Measure for 3D Skeleton Sequences via Temporal-Viewpoint Alignment
Authors:
Lei Wang,
Jun Liu,
Liang Zheng,
Tom Gedeon,
Piotr Koniusz
Abstract:
Video sequences exhibit significant nuisance variations (undesired effects) of speed of actions, temporal locations, and subjects' poses, leading to temporal-viewpoint misalignment when comparing two sets of frames or evaluating the similarity of two sequences. Thus, we propose Joint tEmporal and cAmera viewpoiNt alIgnmEnt (JEANIE) for sequence pairs. In particular, we focus on 3D skeleton sequenc…
▽ More
Video sequences exhibit significant nuisance variations (undesired effects) of speed of actions, temporal locations, and subjects' poses, leading to temporal-viewpoint misalignment when comparing two sets of frames or evaluating the similarity of two sequences. Thus, we propose Joint tEmporal and cAmera viewpoiNt alIgnmEnt (JEANIE) for sequence pairs. In particular, we focus on 3D skeleton sequences whose camera and subjects' poses can be easily manipulated in 3D. We evaluate JEANIE on skeletal Few-shot Action Recognition (FSAR), where matching well temporal blocks (temporal chunks that make up a sequence) of support-query sequence pairs (by factoring out nuisance variations) is essential due to limited samples of novel classes. Given a query sequence, we create its several views by simulating several camera locations. For a support sequence, we match it with view-simulated query sequences, as in the popular Dynamic Time Warping (DTW). Specifically, each support temporal block can be matched to the query temporal block with the same or adjacent (next) temporal index, and adjacent camera views to achieve joint local temporal-viewpoint warping. JEANIE selects the smallest distance among matching paths with different temporal-viewpoint warping patterns, an advantage over DTW which only performs temporal alignment. We also propose an unsupervised FSAR akin to clustering of sequences with JEANIE as a distance measure. JEANIE achieves state-of-the-art results on NTU-60, NTU-120, Kinetics-skeleton and UWA3D Multiview Activity II on supervised and unsupervised FSAR, and their meta-learning inspired fusion.
△ Less
Submitted 7 February, 2024;
originally announced February 2024.
-
AoSRNet: All-in-One Scene Recovery Networks via Multi-knowledge Integration
Authors:
Yuxu Lu,
Dong Yang,
Yuan Gao,
Ryan Wen Liu,
Jun Liu,
Yu Guo
Abstract:
Scattering and attenuation of light in no-homogeneous imaging media or inconsistent light intensity will cause insufficient contrast and color distortion in the collected images, which limits the developments such as vision-driven smart urban, autonomous vehicles, and intelligent robots. In this paper, we propose an all-in-one scene recovery network via multi-knowledge integration (termed AoSRNet)…
▽ More
Scattering and attenuation of light in no-homogeneous imaging media or inconsistent light intensity will cause insufficient contrast and color distortion in the collected images, which limits the developments such as vision-driven smart urban, autonomous vehicles, and intelligent robots. In this paper, we propose an all-in-one scene recovery network via multi-knowledge integration (termed AoSRNet) to improve the visibility of imaging devices in typical low-visibility imaging scenes (e.g., haze, sand dust, and low light). It combines gamma correction (GC) and optimized linear stretching (OLS) to create the detail enhancement module (DEM) and color restoration module (CRM). Additionally, we suggest a multi-receptive field extraction module (MEM) to attenuate the loss of image texture details caused by GC nonlinear and OLS linear transformations. Finally, we refine the coarse features generated by DEM, CRM, and MEM through Encoder-Decoder to generate the final restored image. Comprehensive experimental results demonstrate the effectiveness and stability of AoSRNet compared to other state-of-the-art methods. The source code is available at \url{https://github.com/LouisYuxuLu/AoSRNet}.
△ Less
Submitted 6 February, 2024;
originally announced February 2024.
-
Non-Stationary Latent Auto-Regressive Bandits
Authors:
Anna L. Trella,
Walter Dempsey,
Finale Doshi-Velez,
Susan A. Murphy
Abstract:
We consider the stochastic multi-armed bandit problem with non-stationary rewards. We present a novel formulation of non-stationarity in the environment where changes in the mean reward of the arms over time are due to some unknown, latent, auto-regressive (AR) state of order $k$. We call this new environment the latent AR bandit. Different forms of the latent AR bandit appear in many real-world s…
▽ More
We consider the stochastic multi-armed bandit problem with non-stationary rewards. We present a novel formulation of non-stationarity in the environment where changes in the mean reward of the arms over time are due to some unknown, latent, auto-regressive (AR) state of order $k$. We call this new environment the latent AR bandit. Different forms of the latent AR bandit appear in many real-world settings, especially in emerging scientific fields such as behavioral health or education where there are few mechanistic models of the environment. If the AR order $k$ is known, we propose an algorithm that achieves $\tilde{O}(k\sqrt{T})$ regret in this setting. Empirically, our algorithm outperforms standard UCB across multiple non-stationary environments, even if $k$ is mis-specified.
△ Less
Submitted 5 February, 2024;
originally announced February 2024.
-
Online Uniform Risk Times Sampling: First Approximation Algorithms, Learning Augmentation with Full Confidence Interval Integration
Authors:
Xueqing Liu,
Kyra Gan,
Esmaeil Keyvanshokooh,
Susan Murphy
Abstract:
In digital health, the strategy of allocating a limited treatment budget across available risk times is crucial to reduce user fatigue. This strategy, however, encounters a significant obstacle due to the unknown actual number of risk times, a factor not adequately addressed by existing methods lacking theoretical guarantees. This paper introduces, for the first time, the online uniform risk times…
▽ More
In digital health, the strategy of allocating a limited treatment budget across available risk times is crucial to reduce user fatigue. This strategy, however, encounters a significant obstacle due to the unknown actual number of risk times, a factor not adequately addressed by existing methods lacking theoretical guarantees. This paper introduces, for the first time, the online uniform risk times sampling problem within the approximation algorithm framework. We propose two online approximation algorithms for this problem, one with and one without learning augmentation, and provide rigorous theoretical performance guarantees for them using competitive ratio analysis. We assess the performance of our algorithms using both synthetic experiments and a real-world case study on HeartSteps mobile applications.
△ Less
Submitted 7 February, 2024; v1 submitted 2 February, 2024;
originally announced February 2024.
-
Source-free Domain Adaptive Object Detection in Remote Sensing Images
Authors:
Weixing Liu,
Jun Liu,
Xin Su,
Han Nie,
Bin Luo
Abstract:
Recent studies have used unsupervised domain adaptive object detection (UDAOD) methods to bridge the domain gap in remote sensing (RS) images. However, UDAOD methods typically assume that the source domain data can be accessed during the domain adaptation process. This setting is often impractical in the real world due to RS data privacy and transmission difficulty. To address this challenge, we p…
▽ More
Recent studies have used unsupervised domain adaptive object detection (UDAOD) methods to bridge the domain gap in remote sensing (RS) images. However, UDAOD methods typically assume that the source domain data can be accessed during the domain adaptation process. This setting is often impractical in the real world due to RS data privacy and transmission difficulty. To address this challenge, we propose a practical source-free object detection (SFOD) setting for RS images, which aims to perform target domain adaptation using only the source pre-trained model. We propose a new SFOD method for RS images consisting of two parts: perturbed domain generation and alignment. The proposed multilevel perturbation constructs the perturbed domain in a simple yet efficient form by perturbing the domain-variant features at the image level and feature level according to the color and style bias. The proposed multilevel alignment calculates feature and label consistency between the perturbed domain and the target domain across the teacher-student network, and introduces the distillation of feature prototype to mitigate the noise of pseudo-labels. By requiring the detector to be consistent in the perturbed domain and the target domain, the detector is forced to focus on domaininvariant features. Extensive results of three synthetic-to-real experiments and three cross-sensor experiments have validated the effectiveness of our method which does not require access to source domain RS images. Furthermore, experiments on computer vision datasets show that our method can be extended to other fields as well. Our code will be available at: https://weixliu.github.io/ .
△ Less
Submitted 31 January, 2024;
originally announced January 2024.
-
Reinforcement Learning Interventions on Boundedly Rational Human Agents in Frictionful Tasks
Authors:
Eura Nofshin,
Siddharth Swaroop,
Weiwei Pan,
Susan Murphy,
Finale Doshi-Velez
Abstract:
Many important behavior changes are frictionful; they require individuals to expend effort over a long period with little immediate gratification. Here, an artificial intelligence (AI) agent can provide personalized interventions to help individuals stick to their goals. In these settings, the AI agent must personalize rapidly (before the individual disengages) and interpretably, to help us unders…
▽ More
Many important behavior changes are frictionful; they require individuals to expend effort over a long period with little immediate gratification. Here, an artificial intelligence (AI) agent can provide personalized interventions to help individuals stick to their goals. In these settings, the AI agent must personalize rapidly (before the individual disengages) and interpretably, to help us understand the behavioral interventions. In this paper, we introduce Behavior Model Reinforcement Learning (BMRL), a framework in which an AI agent intervenes on the parameters of a Markov Decision Process (MDP) belonging to a boundedly rational human agent. Our formulation of the human decision-maker as a planning agent allows us to attribute undesirable human policies (ones that do not lead to the goal) to their maladapted MDP parameters, such as an extremely low discount factor. Furthermore, we propose a class of tractable human models that captures fundamental behaviors in frictionful tasks. Introducing a notion of MDP equivalence specific to BMRL, we theoretically and empirically show that AI planning with our human models can lead to helpful policies on a wide range of more complex, ground-truth humans.
△ Less
Submitted 26 January, 2024;
originally announced January 2024.
-
RIS Empowered Near-Field Covert Communications
Authors:
Jun Liu,
Gang Yang,
Yuanwei Liu,
Xiangyun Zhou
Abstract:
This paper studies an extremely large-scale reconfigurable intelligent surface (XL-RIS) empowered covert communication system in the near-field region. Alice covertly transmits messages to Bob with the assistance of the XL-RIS, while evading detection by Willie. To enhance the covert communication performance, we maximize the achievable covert rate by jointly optimizing the hybrid analog and digit…
▽ More
This paper studies an extremely large-scale reconfigurable intelligent surface (XL-RIS) empowered covert communication system in the near-field region. Alice covertly transmits messages to Bob with the assistance of the XL-RIS, while evading detection by Willie. To enhance the covert communication performance, we maximize the achievable covert rate by jointly optimizing the hybrid analog and digital beamformers at Alice, as well as the reflection coefficient matrix at the XL-RIS. An alternating optimization algorithm is proposed to solve the joint beamforming design problem. For the hybrid beamformer design, a semi-closed-form solution for fully digital beamformer is first obtained by a weighted minimum mean-square error based algorithm, then the baseband digital and analog beamformers at Alice are designed by approximating the fully digital beamformer via manifold optimization. For the XL-RIS's reflection coefficient matrix design, a low-complexity alternating direction method of multipliers based algorithm is proposed to address the challenge of large-scale variables and unit-modulus constraints. Numerical results unveil that i) the near-field communications can achieve a higher covert rate than the far-field covert communications in general, and still realize covert transmission even if Willie is located at the same direction as Bob and closer to the XL-RIS; ii) the proposed algorithm can enhance the covert rate significantly compared to the benchmark schemes; iii) the proposed algorithm leads to a beam diffraction pattern that can bypass Willie and achieve high-rate covert transmission to Bob.
△ Less
Submitted 24 January, 2024;
originally announced January 2024.
-
Left-right Discrepancy for Adversarial Attack on Stereo Networks
Authors:
Pengfei Wang,
Xiaofei Hui,
Beijia Lu,
Nimrod Lilith,
Jun Liu,
Sameer Alam
Abstract:
Stereo matching neural networks often involve a Siamese structure to extract intermediate features from left and right images. The similarity between these intermediate left-right features significantly impacts the accuracy of disparity estimation. In this paper, we introduce a novel adversarial attack approach that generates perturbation noise specifically designed to maximize the discrepancy bet…
▽ More
Stereo matching neural networks often involve a Siamese structure to extract intermediate features from left and right images. The similarity between these intermediate left-right features significantly impacts the accuracy of disparity estimation. In this paper, we introduce a novel adversarial attack approach that generates perturbation noise specifically designed to maximize the discrepancy between left and right image features. Extensive experiments demonstrate the superior capability of our method to induce larger prediction errors in stereo neural networks, e.g. outperforming existing state-of-the-art attack methods by 219% MAE on the KITTI dataset and 85% MAE on the Scene Flow dataset. Additionally, we extend our approach to include a proxy network black-box attack method, eliminating the need for access to stereo neural network. This method leverages an arbitrary network from a different vision task as a proxy to generate adversarial noise, effectively causing the stereo network to produce erroneous predictions. Our findings highlight a notable sensitivity of stereo networks to discrepancies in shallow layer features, offering valuable insights that could guide future research in enhancing the robustness of stereo vision systems.
△ Less
Submitted 13 January, 2024;
originally announced January 2024.
-
AI and Generative AI for Research Discovery and Summarization
Authors:
Mark Glickman,
Yi Zhang
Abstract:
AI and generative AI tools, including chatbots like ChatGPT that rely on large language models (LLMs), have burst onto the scene this year, creating incredible opportunities to increase work productivity and improve our lives. Statisticians and data scientists have begun experiencing the benefits from the availability of these tools in numerous ways, such as the generation of programming code from…
▽ More
AI and generative AI tools, including chatbots like ChatGPT that rely on large language models (LLMs), have burst onto the scene this year, creating incredible opportunities to increase work productivity and improve our lives. Statisticians and data scientists have begun experiencing the benefits from the availability of these tools in numerous ways, such as the generation of programming code from text prompts to analyze data or fit statistical models. One area that these tools can make a substantial impact is in research discovery and summarization. Standalone tools and plugins to chatbots are being developed that allow researchers to more quickly find relevant literature than pre-2023 search tools. Furthermore, generative AI tools have improved to the point where they can summarize and extract the key points from research articles in succinct language. Finally, chatbots based on highly parameterized LLMs can be used to simulate abductive reasoning, which provides researchers the ability to make connections among related technical topics, which can also be used for research discovery. We review the developments in AI and generative AI for research discovery and summarization, and propose directions where these types of tools are likely to head in the future that may be of interest to statistician and data scientists.
△ Less
Submitted 8 January, 2024;
originally announced January 2024.