Get started
Author

Quanquan Gu

Towards Understanding the Mixture-Of-Experts Layer in Deep Learning
2022 · Zixiang Chen, Yihe Deng, et al. · neural information processing systems · 38
Benign Overfitting in Two-Layer Convolutional Neural Networks
2022 · Yuan Cao, Zixiang Chen, et al. · neural information processing systems · 26
PDF
Robust Learning with Progressive Data Expansion Against Spurious Correlation
2023 · Yihe Deng, Yu Yang, et al. · neural information processing systems · 7
PDF
Why Does Sharpness-Aware Minimization Generalize Better Than SGD?
2023 · Zixiang Chen, Junkai Zhang, et al. · neural information processing systems · 7
PDF
Nearly Optimal Algorithms for Linear Contextual Bandits with Adversarial Corruptions
2022 · Jiafan He, Dongruo Zhou, et al. · neural information processing systems · 7
A Simple and Provably Efficient Algorithm for Asynchronous Federated Contextual Linear Bandits
2022 · Jiafan He, Tianhao Wang, et al. · neural information processing systems · 5
PDF
Implicit Bias of Gradient Descent for Two-layer ReLU and Leaky ReLU Networks on Nearly-orthogonal Data
2023 · Yiwen Kou, Zixiang Chen, et al. · neural information processing systems · 4
PDF
Computationally Efficient Horizon-Free Reinforcement Learning for Linear Mixture MDPs
2022 · Dongruo Zhou, Quanquan Gu · neural information processing systems · 4
PDF
Protein Autoregressive Modeling via Multiscale Structure Generation
2026 · Qu, Yanru, Hsieh, Cheng-Yen, et al. · arXiv (Cornell University) · 1
PDF
Corruption-Robust Offline Reinforcement Learning with General Function Approximation
2023 · Chenlu Ye, Rui Yang, et al. · neural information processing systems · 1
Nearly Minimax Optimal Regret for Adversarial Linear Bandits with Strong Corruptions
2026 · Di, Qiwei, Gu, Quanquan · arXiv (Cornell University)
PDF
Learning Personalized Memory Gating from Delayed One-Sided Feedback
2026 · Ji, Kaixuan, Chen, Zixiang, et al. · arXiv (Cornell University)
PDF
Understanding Off- vs On-Policy Distillation: A Tale of Distinct Training Objectives
2026 · Di, Qiwei, Li, Xuheng, et al. · arXiv (Cornell University)
PDF
Bandits with Multiple Optimal Arms: Minimax Regret and Non-Adaptivity
2026 · Ji, Kaixuan, Di, Qiwei, et al. · arXiv (Cornell University)
PDF
Saturation-Insensitive Dueling Bandits with General Function Approximation
2026 · Zhang, Chenggong, Li, Xuheng, et al. · arXiv (Cornell University)
PDF
Fast Weight Attention for Continual Learning
2026 · Zhang, Yifan, Ta, Steve, et al. · arXiv (Cornell University)
PDF
Breaking the Total Variance Barrier: Sharp Sample Complexity for Linear Heteroscedastic Bandits with Fixed Action Set
2026 · Zhao, Heyang, Jin, Tianyuan, et al. · arXiv (Cornell University)
PDF
Multi-Mask Diffusion Language Models for Few-Step Generation
2026 · Chen, Sijin, Ren, Yinuo, et al. · arXiv (Cornell University)
PDF
DeepLoop: Depth Scaling for Looped Transformers
2026 · Li, Shuzhen, Zhang, Yifan, et al. · arXiv (Cornell University)
PDF
Unlocking Feature Learning in Gated Delta Networks at Scale
2026 · Liu, Yifeng, Gu, Quanquan · arXiv (Cornell University)
PDF
Self-Distilled Policy Gradient
2026 · Liu, Yifeng, Zhang, Shiyuan, et al. · arXiv (Cornell University)
PDF
Fast Rates for Offline Contextual Bandits with Forward-KL Regularization under Single-Policy Concentrability
2026 · Zhao, Qingyue, Ji, Kaixuan, et al. · arXiv (Cornell University)
PDF
Transformers Trained via Gradient Descent Can Provably Learn a Class of Teacher Models
2026 · Zhang, Chenyang, Zhao, Qingyue, et al. · arXiv (Cornell University)
PDF
Near-Optimal Regret for KL-Regularized Multi-Armed Bandits
2026 · Ji, Kaixuan, Zhao, Qingyue, et al. · arXiv (Cornell University)
PDF
Dimension-Independent Convergence of Underdamped Langevin Monte Carlo in KL Divergence
2026 · Zhang, Shiyuan, Di, Qiwei, et al. · arXiv (Cornell University)
PDF
Works count: 31
Citation count: 100
H-index: 5
I10-index: 2
Year
Topic
Type