Picture for Quanquan Gu

Quanquan Gu

Learning Two-Player Mixture Markov Games: Kernel Function Approximation and Correlated Equilibrium

Add code
Aug 10, 2022
Viaarxiv icon

Towards Understanding Mixture of Experts in Deep Learning

Add code
Aug 04, 2022
Figure 1 for Towards Understanding Mixture of Experts in Deep Learning
Figure 2 for Towards Understanding Mixture of Experts in Deep Learning
Figure 3 for Towards Understanding Mixture of Experts in Deep Learning
Figure 4 for Towards Understanding Mixture of Experts in Deep Learning
Viaarxiv icon

The Power and Limitation of Pretraining-Finetuning for Linear Regression under Covariate Shift

Add code
Aug 03, 2022
Figure 1 for The Power and Limitation of Pretraining-Finetuning for Linear Regression under Covariate Shift
Figure 2 for The Power and Limitation of Pretraining-Finetuning for Linear Regression under Covariate Shift
Viaarxiv icon

A Simple and Provably Efficient Algorithm for Asynchronous Federated Contextual Linear Bandits

Add code
Jul 07, 2022
Figure 1 for A Simple and Provably Efficient Algorithm for Asynchronous Federated Contextual Linear Bandits
Figure 2 for A Simple and Provably Efficient Algorithm for Asynchronous Federated Contextual Linear Bandits
Figure 3 for A Simple and Provably Efficient Algorithm for Asynchronous Federated Contextual Linear Bandits
Viaarxiv icon

Computationally Efficient Horizon-Free Reinforcement Learning for Linear Mixture MDPs

Add code
May 23, 2022
Figure 1 for Computationally Efficient Horizon-Free Reinforcement Learning for Linear Mixture MDPs
Viaarxiv icon

Nearly Optimal Algorithms for Linear Contextual Bandits with Adversarial Corruptions

Add code
May 13, 2022
Figure 1 for Nearly Optimal Algorithms for Linear Contextual Bandits with Adversarial Corruptions
Viaarxiv icon

On the Convergence of Certified Robust Training with Interval Bound Propagation

Add code
Mar 16, 2022
Figure 1 for On the Convergence of Certified Robust Training with Interval Bound Propagation
Viaarxiv icon

Risk Bounds of Multi-Pass SGD for Least Squares in the Interpolation Regime

Add code
Mar 07, 2022
Figure 1 for Risk Bounds of Multi-Pass SGD for Least Squares in the Interpolation Regime
Figure 2 for Risk Bounds of Multi-Pass SGD for Least Squares in the Interpolation Regime
Viaarxiv icon

Bandit Learning with General Function Classes: Heteroscedastic Noise and Variance-dependent Regret Bounds

Add code
Feb 28, 2022
Figure 1 for Bandit Learning with General Function Classes: Heteroscedastic Noise and Variance-dependent Regret Bounds
Viaarxiv icon

Benign Overfitting in Two-layer Convolutional Neural Networks

Add code
Feb 14, 2022
Figure 1 for Benign Overfitting in Two-layer Convolutional Neural Networks
Viaarxiv icon