arXiv subjects

Yuxin Chen

Publications and source records attributed to Yuxin Chen.

At least 217 records · Page 12Linked to original sources

arXiv2023

Is Q-Learning Minimax Optimal? A Tight Sample Complexity Analysis

Q-learning, which seeks to learn the optimal Q-function of a Markov decision process (MDP) in a model-free fashion, lies at the heart of reinforcement learning. When it comes to the synchronous setting (such that independent samples for all state-action pairs are drawn from a generative model in each iteration), substantial progress has been made towards understanding the sample efficiency of Q-learning. Consider a $γ$-discounted infinite-horizon MDP with state space $\mathcal{S}$ and action space $\mathcal{A}$: to yield an entrywise $\varepsilon$-approximation of the optimal Q-function, state-of-the-art theory for Q-learning requires a sample size exceeding the order of $\frac{|\mathcal{S}||\mathcal{A}|}{(1-γ)^5\varepsilon^{2}}$, which fails to match existing minimax lower bounds. This gives rise to natural questions: what is the sharp sample complexity of Q-learning? Is Q-learning provably sub-optimal? This paper addresses these questions for the synchronous setting: (1) when $|\mathcal{A}|=1$ (so that Q-learning reduces to TD learning), we prove that the sample complexity of TD learning is minimax optimal and scales as $\frac{|\mathcal{S}|}{(1-γ)^3\varepsilon^2}$ (up to log factor); (2) when $|\mathcal{A}|\geq 2$, we settle the sample complexity of Q-learning to be on the order of $\frac{|\mathcal{S}||\mathcal{A}|}{(1-γ)^4\varepsilon^2}$ (up to log factor). Our theory unveils the strict sub-optimality of Q-learning when $|\mathcal{A}|\geq 2$, and rigorizes the negative impact of over-estimation in Q-learning. Finally, we extend our analysis to accommodate asynchronous Q-learning (i.e., the case with Markovian samples), sharpening the horizon dependency of its sample complexity to be $\frac{1}{(1-γ)^4}$.

stat.ML↗

arXiv2023

Learning Human-Compatible Representations for Case-Based Decision Support

Algorithmic case-based decision support provides examples to help human make sense of predicted labels and aid human in decision-making tasks. Despite the promising performance of supervised learning, representations learned by supervised models may not align well with human intuitions: what models consider as similar examples can be perceived as distinct by humans. As a result, they have limited effectiveness in case-based decision support. In this work, we incorporate ideas from metric learning with supervised learning to examine the importance of alignment for effective decision support. In addition to instance-level labels, we use human-provided triplet judgments to learn human-compatible decision-focused representations. Using both synthetic data and human subject experiments in multiple classification tasks, we demonstrate that such representation is better aligned with human perception than representation solely optimized for classification. Human-compatible representations identify nearest neighbors that are perceived as more similar by humans and allow humans to make more accurate predictions, leading to substantial improvements in human decision accuracies (17.8% in butterfly vs. moth classification and 13.2% in pneumonia classification).

cs.LG↗

arXiv2023

Scalable Batch-Mode Deep Bayesian Active Learning via Equivalence Class Annealing

Active learning has demonstrated data efficiency in many fields. Existing active learning algorithms, especially in the context of batch-mode deep Bayesian active models, rely heavily on the quality of uncertainty estimations of the model, and are often challenging to scale to large batches. In this paper, we propose Batch-BALanCe, a scalable batch-mode active learning algorithm, which combines insights from decision-theoretic active learning, combinatorial information measure, and diversity sampling. At its core, Batch-BALanCe relies on a novel decision-theoretic acquisition function that facilitates differentiation among different equivalence classes. Intuitively, each equivalence class consists of hypotheses (e.g., posterior samples of deep neural networks) with similar predictions, and Batch-BALanCe adaptively adjusts the size of the equivalence classes as learning progresses. To scale up the computation of queries to large batches, we further propose an efficient batch-mode acquisition procedure, which aims to maximize a novel information measure defined through the acquisition function. We show that our algorithm can effectively handle realistic multi-class classification tasks, and achieves compelling performance on several benchmark datasets for active learning under both low- and large-batch regimes. Reference code is released at https://github.com/zhangrenyuuchicago/BALanCe.

cs.LG↗

arXiv2023

Online Learning of Energy Consumption for Navigation of Electric Vehicles

Energy efficient navigation constitutes an important challenge in electric vehicles, due to their limited battery capacity. We employ a Bayesian approach to model the energy consumption at road segments for efficient navigation. In order to learn the model parameters, we develop an online learning framework and investigate several exploration strategies such as Thompson Sampling and Upper Confidence Bound. We then extend our online learning framework to the multi-agent setting, where multiple vehicles adaptively navigate and learn the parameters of the energy model. We analyze Thompson Sampling and establish rigorous regret bounds on its performance in the single-agent and multi-agent settings, through an analysis of the algorithm under batched feedback. Finally, we demonstrate the performance of our methods via experiments on several real-world city road networks.

cs.LG↗

arXiv2023

On the Permanence of Backdoors in Evolving Models

Existing research on training-time attacks for deep neural networks (DNNs), such as backdoors, largely assume that models are static once trained, and hidden backdoors trained into models remain active indefinitely. In practice, models are rarely static but evolve continuously to address distribution drifts in the underlying data. This paper explores the behavior of backdoor attacks in time-varying models, whose model weights are continually updated via fine-tuning to adapt to data drifts. Our theoretical analysis shows how fine-tuning with fresh data progressively "erases" the injected backdoors, and our empirical study illustrates how quickly a time-varying model "forgets" backdoors under a variety of training and attack settings. We also show that novel fine-tuning strategies using smart learning rates can significantly accelerate backdoor forgetting. Finally, we discuss the need for new backdoor defenses that target time-varying models specifically.

cs.CR↗

arXiv2023

Policy Mirror Descent for Regularized Reinforcement Learning: A Generalized Framework with Linear Convergence

Policy optimization, which finds the desired policy by maximizing value functions via optimization techniques, lies at the heart of reinforcement learning (RL). In addition to value maximization, other practical considerations arise as well, including the need of encouraging exploration, and that of ensuring certain structural properties of the learned policy due to safety, resource and operational constraints. These can often be accounted for via regularized RL, which augments the target value function with a structure-promoting regularizer. Focusing on discounted infinite-horizon Markov decision processes, we propose a generalized policy mirror descent (GPMD) algorithm for solving regularized RL. As a generalization of policy mirror descent (arXiv:2102.00135), our algorithm accommodates a general class of convex regularizers and promotes the use of Bregman divergence in cognizant of the regularizer in use. We demonstrate that our algorithm converges linearly to the global solution over an entire range of learning rates, in a dimension-free fashion, even when the regularizer lacks strong convexity and smoothness. In addition, this linear convergence feature is provably stable in the face of inexact policy evaluation and imperfect policy updates. Numerical experiments are provided to corroborate the appealing performance of GPMD.

cs.LG↗

arXiv2022

Trip Prediction by Leveraging Trip Histories from Neighboring Users

We propose a novel approach for trip prediction by analyzing user's trip histories. We augment users' (self-) trip histories by adding 'similar' trips from other users, which could be informative and useful for predicting future trips for a given user. This also helps to cope with noisy or sparse trip histories, where the self-history by itself does not provide a reliable prediction of future trips. We show empirical evidence that by enriching the users' trip histories with additional trips, one can improve the prediction error by 15%-40%, evaluated on multiple subsets of the Nancy2012 dataset. This real-world dataset is collected from public transportation ticket validations in the city of Nancy, France. Our prediction tool is a central component of a trip simulator system designed to analyze the functionality of public transportation in the city of Nancy.

cs.AI↗

arXiv2022

Softmax Policy Gradient Methods Can Take Exponential Time to Converge

The softmax policy gradient (PG) method, which performs gradient ascent under softmax policy parameterization, is arguably one of the de facto implementations of policy optimization in modern reinforcement learning. For $γ$-discounted infinite-horizon tabular Markov decision processes (MDPs), remarkable progress has recently been achieved towards establishing global convergence of softmax PG methods in finding a near-optimal policy. However, prior results fall short of delineating clear dependencies of convergence rates on salient parameters such as the cardinality of the state space $\mathcal{S}$ and the effective horizon $\frac{1}{1-γ}$, both of which could be excessively large. In this paper, we deliver a pessimistic message regarding the iteration complexity of softmax PG methods, despite assuming access to exact gradient computation. Specifically, we demonstrate that the softmax PG method with stepsize $η$ can take \[ \frac{1}η |\mathcal{S}|^{2^{Ω\big(\frac{1}{1-γ}\big)}} ~\text{iterations} \] to converge, even in the presence of a benign policy initialization and an initial state distribution amenable to exploration (so that the distribution mismatch coefficient is not exceedingly large). This is accomplished by characterizing the algorithmic dynamics over a carefully-constructed MDP containing only three actions. Our exponential lower bound hints at the necessity of carefully adjusting update rules or enforcing proper regularization in accelerating PG methods.

cs.LG↗

arXiv2022

Breaking the Sample Complexity Barrier to Regret-Optimal Model-Free Reinforcement Learning

Achieving sample efficiency in online episodic reinforcement learning (RL) requires optimally balancing exploration and exploitation. When it comes to a finite-horizon episodic Markov decision process with $S$ states, $A$ actions and horizon length $H$, substantial progress has been achieved towards characterizing the minimax-optimal regret, which scales on the order of $\sqrt{H^2SAT}$ (modulo log factors) with $T$ the total number of samples. While several competing solution paradigms have been proposed to minimize regret, they are either memory-inefficient, or fall short of optimality unless the sample size exceeds an enormous threshold (e.g., $S^6A^4 \,\mathrm{poly}(H)$ for existing model-free methods). To overcome such a large sample size barrier to efficient RL, we design a novel model-free algorithm, with space complexity $O(SAH)$, that achieves near-optimal regret as soon as the sample size exceeds the order of $SA\,\mathrm{poly}(H)$. In terms of this sample size requirement (also referred to the initial burn-in cost), our method improves -- by at least a factor of $S^5A^3$ -- upon any prior memory-efficient algorithm that is asymptotically regret-optimal. Leveraging the recently introduced variance reduction strategy (also called {\em reference-advantage decomposition}), the proposed algorithm employs an {\em early-settled} reference update rule, with the aid of two Q-learning sequences with upper and lower confidence bounds. The design principle of our early-settled variance reduction method might be of independent interest to other RL settings that involve intricate exploration-exploitation trade-offs.

cs.LG↗

arXiv2022

Minimax-Optimal Multi-Agent RL in Markov Games With a Generative Model

This paper studies multi-agent reinforcement learning in Markov games, with the goal of learning Nash equilibria or coarse correlated equilibria (CCE) sample-optimally. All prior results suffer from at least one of the two obstacles: the curse of multiple agents and the barrier of long horizon, regardless of the sampling protocol in use. We take a step towards settling this problem, assuming access to a flexible sampling mechanism: the generative model. Focusing on non-stationary finite-horizon Markov games, we develop a fast learning algorithm called \myalg~and an adaptive sampling scheme that leverage the optimism principle in online adversarial learning (particularly the Follow-the-Regularized-Leader (FTRL) method). Our algorithm learns an $\varepsilon$-approximate CCE in a general-sum Markov game using $$ \widetilde{O}\bigg( \frac{H^4 S \sum_{i=1}^m A_i}{\varepsilon^2} \bigg) $$ samples, where $m$ is the number of players, $S$ indicates the number of states, $H$ is the horizon, and $A_i$ denotes the number of actions for the $i$-th player. This is minimax-optimal (up to log factor) when the number of players is fixed. When applied to two-player zero-sum Markov games, our algorithm provably finds an $\varepsilon$-approximate Nash equilibrium with minimal samples. Along the way, we derive a refined regret bound for FTRL that makes explicit the role of variance-type quantities, which might be of independent interest.

cs.LG↗

arXiv2022

PIC 4th Challenge: Semantic-Assisted Multi-Feature Encoding and Multi-Head Decoding for Dense Video Captioning

The task of Dense Video Captioning (DVC) aims to generate captions with timestamps for multiple events in one video. Semantic information plays an important role for both localization and description of DVC. We present a semantic-assisted dense video captioning model based on the encoding-decoding framework. In the encoding stage, we design a concept detector to extract semantic information, which is then fused with multi-modal visual features to sufficiently represent the input video. In the decoding stage, we design a classification head, paralleled with the localization and captioning heads, to provide semantic supervision. Our method achieves significant improvements on the YouMakeup dataset under DVC evaluation metrics and achieves high performance in the Makeup Dense Video Captioning (MDVC) task of PIC 4th Challenge.

cs.CV↗

arXiv2022

Minimax Estimation of Linear Functions of Eigenvectors in the Face of Small Eigen-Gaps

Eigenvector perturbation analysis plays a vital role in various data science applications. A large body of prior works, however, focused on establishing $\ell_{2}$ eigenvector perturbation bounds, which are often highly inadequate in addressing tasks that rely on fine-grained behavior of an eigenvector. This paper makes progress on this by studying the perturbation of linear functions of an unknown eigenvector. Focusing on two fundamental problems -- matrix denoising and principal component analysis -- in the presence of Gaussian noise, we develop a suite of statistical theory that characterizes the perturbation of arbitrary linear functions of an unknown eigenvector. In order to mitigate a non-negligible bias issue inherent to the natural ``plug-in'' estimator, we develop de-biased estimators that (1) achieve minimax lower bounds for a family of scenarios (modulo some logarithmic factor), and (2) can be computed in a data-driven manner without sample splitting. Noteworthily, the proposed estimators are nearly minimax optimal even when the associated eigen-gap is {\em substantially smaller} than what is required in prior statistical theory.

math.ST↗

arXiv2022

Class-wise Thresholding for Robust Out-of-Distribution Detection

We consider the problem of detecting OoD(Out-of-Distribution) input data when using deep neural networks, and we propose a simple yet effective way to improve the robustness of several popular OoD detection methods against label shift. Our work is motivated by the observation that most existing OoD detection algorithms consider all training/test data as a whole, regardless of which class entry each input activates (inter-class differences). Through extensive experimentation, we have found that such practice leads to a detector whose performance is sensitive and vulnerable to label shift. To address this issue, we propose a class-wise thresholding scheme that can apply to most existing OoD detection algorithms and can maintain similar OoD detection performance even in the presence of label shift in the test distribution.

cs.LG↗

arXiv2022

Pessimistic Q-Learning for Offline Reinforcement Learning: Towards Optimal Sample Complexity

Offline or batch reinforcement learning seeks to learn a near-optimal policy using history data without active exploration of the environment. To counter the insufficient coverage and sample scarcity of many offline datasets, the principle of pessimism has been recently introduced to mitigate high bias of the estimated values. While pessimistic variants of model-based algorithms (e.g., value iteration with lower confidence bounds) have been theoretically investigated, their model-free counterparts -- which do not require explicit model estimation -- have not been adequately studied, especially in terms of sample efficiency. To address this inadequacy, we study a pessimistic variant of Q-learning in the context of finite-horizon Markov decision processes, and characterize its sample complexity under the single-policy concentrability assumption which does not require the full coverage of the state-action space. In addition, a variance-reduced pessimistic Q-learning algorithm is proposed to achieve near-optimal sample complexity. Altogether, this work highlights the efficiency of model-free algorithms in offline RL when used in conjunction with pessimism and variance reduction.

cs.LG↗

arXiv2022

These Maps Are Made For Walking: Real-Time Terrain Property Estimation for Mobile Robots

The equations of motion governing mobile robots are dependent on terrain properties such as the coefficient of friction, and contact model parameters. Estimating these properties is thus essential for robotic navigation. Ideally any map estimating terrain properties should run in real time, mitigate sensor noise, and provide probability distributions of the aforementioned properties, thus enabling risk-mitigating navigation and planning. This paper addresses these needs and proposes a Bayesian inference framework for semantic mapping which recursively estimates both the terrain surface profile and a probability distribution for terrain properties using data from a single RGB-D camera. The proposed framework is evaluated in simulation against other semantic mapping methods and is shown to outperform these state-of-the-art methods in terms of correctly estimating simulated ground-truth terrain properties when evaluated using a precision-recall curve and the Kullback-Leibler divergence test. Additionally, the proposed method is deployed on a physical legged robotic platform in both indoor and outdoor environments, and we show our method correctly predicts terrain properties in both cases. The proposed framework runs in real-time and includes a ROS interface for easy integration.

cs.RO↗

arXiv2022

CREATE: A Benchmark for Chinese Short Video Retrieval and Title Generation

Previous works of video captioning aim to objectively describe the video's actual content, which lacks subjective and attractive expression, limiting its practical application scenarios. Video titling is intended to achieve this goal, but there is a lack of a proper benchmark. In this paper, we propose to CREATE, the first large-scale Chinese shoRt vidEo retrievAl and Title gEneration benchmark, to facilitate research and application in video titling and video retrieval in Chinese. CREATE consists of a high-quality labeled 210K dataset and two large-scale 3M/10M pre-training datasets, covering 51 categories, 50K+ tags, 537K manually annotated titles and captions, and 10M+ short videos. Based on CREATE, we propose a novel model ALWIG which combines video retrieval and video titling tasks to achieve the purpose of multi-modal ALignment WIth Generation with the help of video tags and a GPT pre-trained model. CREATE opens new directions for facilitating future research and applications on video titling and video retrieval in the field of Chinese short videos.

cs.CV↗

arXiv2022

Open-Vocabulary One-Stage Detection with Hierarchical Visual-Language Knowledge Distillation

Open-vocabulary object detection aims to detect novel object categories beyond the training set. The advanced open-vocabulary two-stage detectors employ instance-level visual-to-visual knowledge distillation to align the visual space of the detector with the semantic space of the Pre-trained Visual-Language Model (PVLM). However, in the more efficient one-stage detector, the absence of class-agnostic object proposals hinders the knowledge distillation on unseen objects, leading to severe performance degradation. In this paper, we propose a hierarchical visual-language knowledge distillation method, i.e., HierKD, for open-vocabulary one-stage detection. Specifically, a global-level knowledge distillation is explored to transfer the knowledge of unseen categories from the PVLM to the detector. Moreover, we combine the proposed global-level knowledge distillation and the common instance-level knowledge distillation to learn the knowledge of seen and unseen categories simultaneously. Extensive experiments on MS-COCO show that our method significantly surpasses the previous best one-stage detector with 11.9\% and 6.7\% $AP_{50}$ gains under the zero-shot detection and generalized zero-shot detection settings, and reduces the $AP_{50}$ performance gap from 14\% to 7.3\% compared to the best two-stage detector.

cs.CV↗

arXiv2022

Learning Representation for Bayesian Optimization with Collision-free Regularization

Bayesian optimization has been challenged by datasets with large-scale, high-dimensional, and non-stationary characteristics, which are common in real-world scenarios. Recent works attempt to handle such input by applying neural networks ahead of the classical Gaussian process to learn a latent representation. We show that even with proper network design, such learned representation often leads to collision in the latent space: two points with significantly different observations collide in the learned latent space, leading to degraded optimization performance. To address this issue, we propose LOCo, an efficient deep Bayesian optimization framework which employs a novel regularizer to reduce the collision in the learned latent space and encourage the mapping from the latent space to the objective value to be Lipschitz continuous. LOCo takes in pairs of data points and penalizes those too close in the latent space compared to their target space distance. We provide a rigorous theoretical justification for LOCo by inspecting the regret of this dynamic-embedding-based Bayesian optimization algorithm, where the neural network is iteratively retrained with the regularizer. Our empirical results demonstrate the effectiveness of LOCo on several synthetic and real-world benchmark Bayesian optimization tasks.

cs.LG↗