Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Quanquan Gu

Risk Bounds for Over-parameterized Maximum Margin Classification on Sub-Gaussian Mixtures


Apr 28, 2021
Yuan Cao, Quanquan Gu, Mikhail Belkin

* 35 pages, 3 figures 

  Access Paper or Ask Questions

Provable Robustness of Adversarial Training for Learning Halfspaces with Noise


Apr 19, 2021
Difan Zou, Spencer Frei, Quanquan Gu

* 42 pages, 2 figures 

  Access Paper or Ask Questions

Benign Overfitting of Constant-Stepsize SGD for Linear Regression


Mar 23, 2021
Difan Zou, Jingfeng Wu, Vladimir Braverman, Quanquan Gu, Sham M. Kakade

* 53 pages 

  Access Paper or Ask Questions

Batched Neural Bandits


Feb 25, 2021
Quanquan Gu, Amin Karbasi, Khashayar Khosravi, Vahab Mirrokni, Dongruo Zhou

* 21 pages, 7 figures 

  Access Paper or Ask Questions

Nearly Optimal Regret for Learning Adversarial MDPs with Linear Function Approximation


Feb 17, 2021
Jiafan He, Dongruo Zhou, Quanquan Gu

* 28 pages 

  Access Paper or Ask Questions

Almost Optimal Algorithms for Two-player Markov Games with Linear Function Approximation


Feb 15, 2021
Zixiang Chen, Dongruo Zhou, Quanquan Gu

* 31 pages 

  Access Paper or Ask Questions

Nearly Minimax Optimal Regret for Learning Infinite-horizon Average-reward MDPs with Linear Function Approximation


Feb 15, 2021
Yue Wu, Dongruo Zhou, Quanquan Gu

* 40 pages, 1 figure 

  Access Paper or Ask Questions

Provable Generalization of SGD-trained Neural Networks of Any Width in the Presence of Adversarial Label Noise


Jan 14, 2021
Spencer Frei, Yuan Cao, Quanquan Gu

* 29 pages, 9 figures 

  Access Paper or Ask Questions

Nearly Minimax Optimal Reinforcement Learning for Linear Mixture Markov Decision Processes


Jan 07, 2021
Dongruo Zhou, Quanquan Gu, Csaba Szepesvari

* 59 pages, 1 figure 

  Access Paper or Ask Questions

Provably Efficient Reinforcement Learning with Linear Function Approximation Under Adaptivity Constraints


Jan 06, 2021
Tianhao Wang, Dongruo Zhou, Quanquan Gu

* 17 pages 

  Access Paper or Ask Questions

Neural Contextual Bandits with Deep Representation and Shallow Exploration


Dec 03, 2020
Pan Xu, Zheng Wen, Handong Zhao, Quanquan Gu

* 28 pages, 1 figure, 1 table 

  Access Paper or Ask Questions

Logarithmic Regret for Reinforcement Learning with Linear Function Approximation


Nov 23, 2020
Jiafan He, Dongruo Zhou, Quanquan Gu

* 20 pages 

  Access Paper or Ask Questions

Provable Multi-Objective Reinforcement Learning with Generative Models


Nov 19, 2020
Dongruo Zhou, Jiahao Chen, Quanquan Gu

* 10 pages, Workshop on Real-World Reinforcement Learning at the 34th Conference on Neural Information ProcessingSystems (NeurIPS 2020), Vancouver, Canada 

  Access Paper or Ask Questions

Direction Matters: On the Implicit Regularization Effect of Stochastic Gradient Descent with Moderate Learning Rate


Nov 04, 2020
Jingfeng Wu, Difan Zou, Vladimir Braverman, Quanquan Gu


  Access Paper or Ask Questions

Faster Convergence of Stochastic Gradient Langevin Dynamics for Non-Log-Concave Sampling


Oct 19, 2020
Difan Zou, Pan Xu, Quanquan Gu

* 42 pages, 1 figure 

  Access Paper or Ask Questions

Does Network Width Really Help Adversarial Robustness?


Oct 03, 2020
Boxi Wu, Jinghui Chen, Deng Cai, Xiaofei He, Quanquan Gu

* 19 pages, 4 tables, 4 figures 

  Access Paper or Ask Questions

Efficient Robust Training via Backward Smoothing


Oct 03, 2020
Jinghui Chen, Yu Cheng, Zhe Gan, Quanquan Gu, Jingjing Liu

* 12 pages, 11 tables, 5 figures 

  Access Paper or Ask Questions

Neural Thompson Sampling


Oct 02, 2020
Weitong Zhang, Dongruo Zhou, Lihong Li, Quanquan Gu

* 32 pages, 2 tables, 4 figures 

  Access Paper or Ask Questions

Minimax Optimal Reinforcement Learning for Discounted MDPs


Oct 01, 2020
Jiafan He, Dongruo Zhou, Quanquan Gu

* 34 pages, 1 table 

  Access Paper or Ask Questions

Agnostic Learning of Halfspaces with Gradient Descent via Soft Margins


Oct 01, 2020
Spencer Frei, Yuan Cao, Quanquan Gu

* 24 pages, 1 table 

  Access Paper or Ask Questions

Provably Efficient Reinforcement Learning for Discounted MDPs with Feature Mapping


Jun 23, 2020
Dongruo Zhou, Jiafan He, Quanquan Gu

* 28 pages, 1 figure 

  Access Paper or Ask Questions

RayS: A Ray Searching Method for Hard-label Adversarial Attack


Jun 23, 2020
Jinghui Chen, Quanquan Gu

* 9 pages, 4 figures, 9 tables. In KDD 2020 

  Access Paper or Ask Questions

Revisiting Membership Inference Under Realistic Assumptions


Jun 21, 2020
Bargav Jayaraman, Lingxiao Wang, David Evans, Quanquan Gu


  Access Paper or Ask Questions

Optimization Theory for ReLU Neural Networks Trained with Normalization Layers


Jun 11, 2020
Yonatan Dukler, Quanquan Gu, Guido Montúfar

* To be presented at ICML 2020 

  Access Paper or Ask Questions

Agnostic Learning of a Single Neuron with Gradient Descent


Jun 11, 2020
Spencer Frei, Yuan Cao, Quanquan Gu

* 28 pages, 3 tables 

  Access Paper or Ask Questions

A Finite Time Analysis of Two Time-Scale Actor Critic Methods


May 04, 2020
Yue Wu, Weitong Zhang, Pan Xu, Quanquan Gu

* 43 pages 

  Access Paper or Ask Questions