no code implementations • ICML 2020 • Chen Dan, Yuting Wei, Pradeep Ravikumar
In this paper, we provide the first result of the \emph{optimal} minimax guarantees for the excess risk for adversarially robust classification, under Gaussian mixture model proposed by \cite{schmidt2018adversarially}.
no code implementations • 24 Oct 2024 • Zhihan Huang, Yuting Wei, Yuxin Chen
The denoising diffusion probabilistic model (DDPM) has emerged as a mainstream generative model in generative AI.
no code implementations • 21 Oct 2024 • Weichen Wu, Gen Li, Yuting Wei, Alessandro Rinaldo
Statistical inference with finite-sample validity for the value function of a given policy in Markov decision processes (MDPs) is crucial for ensuring the reliability of reinforcement learning.
no code implementations • 7 Oct 2024 • Yuchen Wu, Yuxin Chen, Yuting Wei
Diffusion models play a pivotal role in contemporary generative modeling, claiming state-of-the-art performance across various domains.
no code implementations • 8 Aug 2024 • Kevin Tan, Wei Fan, Yuting Wei
Hybrid Reinforcement Learning (RL), where an agent learns from both an offline dataset and online explorations in an unknown environment, has garnered significant recent interest.
no code implementations • 5 Aug 2024 • Gen Li, Yuting Wei, Yuejie Chi, Yuxin Chen
Diffusion models, which convert noise into new data instances by learning to reverse a diffusion process, have become a cornerstone in contemporary generative modeling.
1 code implementation • 11 Mar 2024 • Yuting Wei, Yuanxing Xu, Xinru Wei, Simin Yang, Yangfu Zhu, Yuqing Li, Di Liu, Bin Wu
Given the importance of ancient Chinese in capturing the essence of rich historical and cultural heritage, the rapid advancements in Large Language Models (LLMs) necessitate benchmarks that can effectively evaluate their understanding of ancient contexts.
no code implementations • 6 Mar 2024 • Gen Li, Yu Huang, Timofey Efimov, Yuting Wei, Yuejie Chi, Yuxin Chen
Score-based diffusion models, while achieving remarkable empirical performance, often suffer from low sampling speed, due to extensive function evaluations needed during the sampling phase.
no code implementations • 3 Mar 2024 • Yuchen Wu, Minshuo Chen, Zihao Li, Mengdi Wang, Yuting Wei
Diffusion models benefit from instillation of task-specific information into the score function to steer the sample generation towards desired properties.
no code implementations • 12 Feb 2024 • Gen Li, Zhihan Huang, Yuting Wei
Consistency models, which were proposed to mitigate the high computational overhead during the sampling phase of diffusion models, facilitate single-step sampling while attaining state-of-the-art empirical performance.
no code implementations • 8 Jan 2024 • Gen Li, Yuting Wei
Characterizing the distribution of high-dimensional statistical estimators is a challenging task, due to the breakdown of classical asymptotic theory in high dimension.
no code implementations • 1 Nov 2023 • Tong Yang, Shicong Cen, Yuting Wei, Yuxin Chen, Yuejie Chi
Federated reinforcement learning (RL) enables collaborative decision making of multiple distributed agents without sharing local data trajectories.
no code implementations • 19 Oct 2023 • Yuanxing Xu, Yuting Wei, Bin Wu
This model adeptly selects frames pertinent to queries, obviating the need for a complete movie-level knowledge graph.
no code implementations • 15 Jun 2023 • Gen Li, Yuting Wei, Yuxin Chen, Yuejie Chi
Diffusion models, which convert noise into new data instances by learning to reverse a Markov diffusion process, have become a cornerstone in contemporary generative modeling.
no code implementations • 30 May 2023 • Gen Li, Weichen Wu, Yuejie Chi, Cong Ma, Alessandro Rinaldo, Yuting Wei
This paper is concerned with the problem of policy evaluation with linear function approximation in discounted infinite horizon Markov decision processes.
no code implementations • NeurIPS 2023 • Laixi Shi, Gen Li, Yuting Wei, Yuxin Chen, Matthieu Geist, Yuejie Chi
Assuming access to a generative model that draws samples based on the nominal MDP, we characterize the sample complexity of RMDPs when the uncertainty set is specified via either the total variation (TV) distance or $\chi^2$ divergence.
no code implementations • 7 Feb 2023 • Gen Li, Wei Fan, Yuting Wei
This paper is concerned with the problem of reconstructing an unknown rank-one matrix with prior structural information from noisy observations.
no code implementations • 22 Aug 2022 • Gen Li, Yuejie Chi, Yuting Wei, Yuxin Chen
This paper studies multi-agent reinforcement learning in Markov games, with the goal of learning Nash equilibria or coarse correlated equilibria (CCE) sample-optimally.
no code implementations • 5 Aug 2022 • Gen Li, Yuting Wei
As two concrete consequences of the proposed analysis recipe: (i) when solving $\mathbb{Z}_2$ synchronization, we predict the behavior of spectrally initialized AMP for up to $O\big(\frac{n}{\mathrm{poly}\log n}\big)$ iterations, showing that the algorithm succeeds without the need of a subsequent refinement stage (as conjectured recently by \citet{celentano2021local}); (ii) we characterize the non-asymptotic behavior of AMP in sparse PCA (in the spiked Wigner model) for a broad range of signal-to-noise ratio.
no code implementations • 25 May 2022 • Pratik Patil, Arun Kumar Kuchibhotla, Yuting Wei, Alessandro Rinaldo
Recent empirical and theoretical analyses of several commonly used prediction procedures reveal a peculiar risk behavior in high dimensions, referred to as double/multiple descent, in which the asymptotic risk is a non-monotonic function of the limiting aspect ratio of the number of features or parameters to the sample size.
no code implementations • 11 Apr 2022 • Gen Li, Laixi Shi, Yuxin Chen, Yuejie Chi, Yuting Wei
We demonstrate that the model-based (or "plug-in") approach achieves minimax-optimal sample complexity without burn-in cost for tabular Markov decision processes (MDPs).
no code implementations • 28 Feb 2022 • Laixi Shi, Gen Li, Yuting Wei, Yuxin Chen, Yuejie Chi
Offline or batch reinforcement learning seeks to learn a near-optimal policy using history data without active exploration of the environment.
no code implementations • 18 Oct 2021 • Yue Li, Yuting Wei
An evolving line of machine learning works observe empirical evidence that suggests interpolating estimators -- the ones that achieve zero training error -- may not necessarily be harmful.
no code implementations • NeurIPS 2021 • Shicong Cen, Yuting Wei, Yuejie Chi
Motivated by the algorithmic role of entropy regularization in single-agent reinforcement learning and game theory, we develop provably efficient extragradient methods to find the quantal response equilibrium (QRE) -- which are solutions to zero-sum two-player matrix games with entropy regularization -- at a linear rate.
no code implementations • NeurIPS 2021 • Gen Li, Yuxin Chen, Yuejie Chi, Yuantao Gu, Yuting Wei
The current paper pertains to a scenario with value-based linear representation, which postulates the linear realizability of the optimal Q-function (also called the "linear $Q^{\star}$ problem").
no code implementations • 22 Feb 2021 • Gen Li, Yuting Wei, Yuejie Chi, Yuxin Chen
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.
no code implementations • 12 Feb 2021 • Gen Li, Changxiao Cai, Yuxin Chen, Yuting Wei, Yuejie Chi
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 $\frac{|\mathcal{S}|}{(1-\gamma)^3\varepsilon^2}$ (up to log factor); (2) when $|\mathcal{A}|\geq 2$, we settle the sample complexity of Q-learning to be on the order of $\frac{|\mathcal{S}||\mathcal{A}|}{(1-\gamma)^4\varepsilon^2}$ (up to log factor).
2 code implementations • 4 Dec 2020 • Zhimei Ren, Yuting Wei, Emmanuel Candès
Model-X knockoffs is a general procedure that can leverage any feature importance measure to produce a variable selection algorithm, which discovers true effects while rigorously controlling the number or fraction of false positives.
Feature Importance
Variable Selection
Methodology
Applications
1 code implementation • 1 Dec 2020 • Jingyan Wang, Ivan Stelmakh, Yuting Wei, Nihar B. Shah
For example, universities ask students to rate the teaching quality of their instructors, and conference organizers ask authors of submissions to evaluate the quality of the reviews.
no code implementations • NeurIPS 2020 • Yue Li, Ilmun Kim, Yuting Wei
We investigate the problem of testing the global null in the high-dimensional regression models when the feature dimension $p$ grows proportionally to the number of observations $n$.
no code implementations • 27 Jul 2020 • Michael Celentano, Andrea Montanari, Yuting Wei
On the other hand, the Lasso estimator can be precisely characterized in the regime in which both $n$ and $p$ are large and $n/p$ is of order one.
no code implementations • 13 Jul 2020 • Shicong Cen, Chen Cheng, Yuxin Chen, Yuting Wei, Yuejie Chi
This class of methods is often applied in conjunction with entropy regularization -- an algorithmic scheme that encourages exploration -- and is closely related to soft policy iteration and trust region policy optimization.
no code implementations • 29 Jun 2020 • Chen Dan, Yuting Wei, Pradeep Ravikumar
In this paper, we provide the first result of the optimal minimax guarantees for the excess risk for adversarially robust classification, under Gaussian mixture model proposed by \cite{schmidt2018adversarially}.
no code implementations • NeurIPS 2020 • Gen Li, Yuting Wei, Yuejie Chi, Yuantao Gu, Yuxin Chen
Focusing on a $\gamma$-discounted MDP with state space $\mathcal{S}$ and action space $\mathcal{A}$, we demonstrate that the $\ell_{\infty}$-based sample complexity of classical asynchronous Q-learning --- namely, the number of samples needed to yield an entrywise $\varepsilon$-accurate estimate of the Q-function --- is at most on the order of $\frac{1}{\mu_{\min}(1-\gamma)^5\varepsilon^2}+ \frac{t_{mix}}{\mu_{\min}(1-\gamma)}$ up to some logarithmic factor, provided that a proper constant learning rate is adopted.
no code implementations • NeurIPS 2020 • Gen Li, Yuting Wei, Yuejie Chi, Yuxin Chen
This paper is concerned with the sample efficiency of reinforcement learning, assuming access to a generative model (or simulator).
no code implementations • 14 Jan 2020 • Chen Cheng, Yuting Wei, Yuxin Chen
This paper aims to address two fundamental challenges arising in eigenvector estimation and inference for a low-rank matrix from noisy observations: (1) how to estimate an unknown eigenvector when the eigen-gap (i. e. the spacing between the associated eigenvalue and the rest of the spectrum) is particularly small; (2) how to perform estimation and inference on linear functionals of an eigenvector -- a sort of "fine-grained" statistical reasoning that goes far beyond the usual $\ell_2$ analysis.
no code implementations • NeurIPS 2017 • Yuting Wei, Fanny Yang, Martin J. Wainwright
Early stopping of iterative algorithms is a widely-used form of regularization in statistics, commonly used in conjunction with boosting and related gradient-type algorithms.
no code implementations • 15 Aug 2015 • Tony Cai, Adityanand Guntuboyina, Yuting Wei
In this paper, we consider adaptive estimation of an unknown planar compact, convex set from noisy measurements of its support function on a uniform grid.
Statistics Theory Statistics Theory