Gen Li

Zhihan Huang

CoRR, 2024

A non-asymptotic distributional theory of approximate message passing for sparse and robust regression.

[BibT_eX]

[DOI]

CoRR, 2024

2023

The Efficacy of Pessimism in Asynchronous Q-Learning.

[BibT_eX]

[DOI]

IEEE Trans. Inf. Theory, November, 2023

Provable Identifiability of Two-Layer ReLU Neural Networks via LASSO Regularization.

[BibT_eX]

[DOI]

Ganghua Wang

IEEE Trans. Inf. Theory, September, 2023

Towards Understanding Variation-Constrained Deep Neural Networks.

[BibT_eX]

[DOI]

IEEE Trans. Signal Process., 2023

Softmax policy gradient methods can take exponential time to converge.

[BibT_eX]

[DOI]

Math. Program., 2023

Towards Faster Non-Asymptotic Convergence for Diffusion-Based Generative Models.

[BibT_eX]

[DOI]

CoRR, 2023

Sharp high-probability sample complexities for policy evaluation with linear function approximation.

[BibT_eX]

[DOI]

CoRR, 2023

Minimax-Optimal Reward-Agnostic Exploration in Reinforcement Learning.

[BibT_eX]

[DOI]

CoRR, 2023

Approximate message passing from random initialization with applications to ℤ2 synchronization.

[BibT_eX]

[DOI]

Wei Fan

CoRR, 2023

Fast Computation of Optimal Transport via Entropy-Regularized Extragradient Methods.

[BibT_eX]

[DOI]

CoRR, 2023

The Curious Price of Distributional Robustness in Reinforcement Learning with a Generative Model.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Reward-agnostic Fine-tuning: Provable Statistical Benefits of Hybrid Reinforcement Learning.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

2022

Sample Complexity of Asynchronous Q-Learning: Sharper Analysis and Variance Reduction.

[BibT_eX]

[DOI]

IEEE Trans. Inf. Theory, 2022

$\ell _1$ Regularization in Two-Layer Neural Networks.

[BibT_eX]

[DOI]

IEEE Signal Process. Lett., 2022

Nonconvex Low-Rank Tensor Completion from Noisy Data.

[BibT_eX]

[DOI]

Oper. Res., 2022

Multi-Agent Reinforcement Learning with Reward Delays.

[BibT_eX]

[DOI]

CoRR, 2022

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

[BibT_eX]

[DOI]

CoRR, 2022

A Non-Asymptotic Framework for Approximate Message Passing in Spiked Models.

[BibT_eX]

[DOI]

CoRR, 2022

Model-Based Reinforcement Learning Is Minimax-Optimal for Offline Zero-Sum Markov Games.

[BibT_eX]

[DOI]

CoRR, 2022

Settling the Sample Complexity of Model-Based Offline Reinforcement Learning.

[BibT_eX]

[DOI]

CoRR, 2022

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

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

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

[BibT_eX]

[DOI]

Proceedings of the International Conference on Machine Learning, 2022

2021

The Rate of Convergence of Variation-Constrained Deep Neural Networks.

[BibT_eX]

[DOI]

CoRR, 2021

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

[BibT_eX]

[DOI]

CoRR, 2021

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

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Sample-Efficient Reinforcement Learning Is Feasible for Linearly Realizable MDPs with Limited Revisiting.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Theory of Spectral Method for Union of Subspaces-Based Random Geometry Graph.

[BibT_eX]

[DOI]

Proceedings of the 38th International Conference on Machine Learning, 2021

Tightening the Dependence on Horizon in the Sample Complexity of Q-Learning.

[BibT_eX]

[DOI]

Proceedings of the 38th International Conference on Machine Learning, 2021

Softmax Policy Gradient Methods Can Take Exponential Time to Converge.

[BibT_eX]

[DOI]

Proceedings of the Conference on Learning Theory, 2021

2020

Unraveling the Veil of Subspace RIP Through Near-Isometry on Subspaces.

[BibT_eX]

[DOI]

Xingyu Xu

IEEE Trans. Signal Process., 2020

Lower Bound for RIP Constants and Concentration of Sum of Top Order Statistics.

[BibT_eX]

[DOI]

Xingyu Xu

IEEE Trans. Signal Process., 2020

The Efficacy of L1s Regularization in Two-Layer Neural Networks.

[BibT_eX]

[DOI]

CoRR, 2020

Breaking the Sample Size Barrier in Model-Based Reinforcement Learning with a Generative Model.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

2019

Nonconvex Low-Rank Symmetric Tensor Completion from Noisy Data.

[BibT_eX]

[DOI]

CoRR, 2019

Subspace Estimation from Unbalanced and Incomplete Data Matrices: 𝓁2, ∞ Statistical Guarantees.

[BibT_eX]

[DOI]

CoRR, 2019

Compressed Subspace Learning Based on Canonical Angle Preserving Property.

[BibT_eX]

[DOI]

CoRR, 2019

Johnson-Lindenstrauss Property Implies Subspace Restricted Isometry Property.

[BibT_eX]

[DOI]

Xingyu Xu

CoRR, 2019

Information Theoretic Lower Bound of Restricted Isometry Property Constant.

[BibT_eX]

[DOI]

Jingkai Yan

Proceedings of the IEEE International Conference on Acoustics, 2019

2018

Restricted Isometry Property of Gaussian Random Projection for Finite Set of Subspaces.

[BibT_eX]

[DOI]

IEEE Trans. Signal Process., 2018

An RIP-Based Performance Guarantee of Covariance-Assisted Matching Pursuit.

[BibT_eX]

[DOI]

IEEE Signal Process. Lett., 2018

Active Orthogonal Matching Pursuit for Sparse Subspace Clustering.

[BibT_eX]

[DOI]

Yanxi Chen

IEEE Signal Process. Lett., 2018

A General Framework for Understanding Compressed Subspace Clustering Algorithms.

[BibT_eX]

[DOI]

IEEE J. Sel. Top. Signal Process., 2018

Rigorous Restricted Isometry Property of Low-Dimensional Subspaces.

[BibT_eX]

[DOI]

Qinghua Liu

CoRR, 2018

Outage Probability Conjecture Does Not Hold for Two-Input-Multiple-Output (TIM 0) System.

[BibT_eX]

[DOI]

Jingkai Yan

Proceedings of the 2018 IEEE International Symposium on Information Theory, 2018

Convergence Analysis on a Fast Iterative Phase Retrieval Algorithm Without Independence Assumption.

[BibT_eX]

[DOI]

Proceedings of the 2018 IEEE International Conference on Acoustics, 2018

Restricted Isometry Property for Low-Dimensional Subspaces and its Application in Compressed Subspace Clustering.

[BibT_eX]

[DOI]

Qinghua Liu

Proceedings of the 2018 IEEE Data Science Workshop, 2018

Subspace Principal Angle Preserving Property of Gaussian Random Projection.

[BibT_eX]

[DOI]

Proceedings of the 2018 IEEE Data Science Workshop, 2018

2017

Linear Convergence of An Iterative Phase Retrieval Algorithm with Data Reuse.

[BibT_eX]

[DOI]

CoRR, 2017

On the Outage Probability Conjecture for MIMO Channels.

[BibT_eX]

[DOI]

Jingkai Yan

CoRR, 2017

Phase Transitions of Spectral Initialization for High-Dimensional Nonconvex Estimation.

[BibT_eX]

[DOI]

Yue M. Lu

CoRR, 2017

Spectral initialization for nonconvex estimation: High-dimensional limit and phase transitions.

[BibT_eX]

[DOI]

Yue M. Lu

Proceedings of the 2017 IEEE International Symposium on Information Theory, 2017

Distance-preserving property of random projection for subspaces.

[BibT_eX]

[DOI]

Proceedings of the 2017 IEEE International Conference on Acoustics, 2017

Principal angles preserving property of Gaussian random projection for subspaces.

[BibT_eX]

[DOI]

Proceedings of the 2017 IEEE Global Conference on Signal and Information Processing, 2017

2015

Phase retrieval using iterative projections: Dynamics in the large systems limit.

[BibT_eX]

[DOI]