Quanquan Gu

70

Papers

135

Total Citations

Papers (70)

How Many Pretraining Tasks Are Needed for In-Context Learning of Linear Regression?

Semiparametric Differential Graph Models

Convergence of Score-Based Discrete Diffusion Models: A Discrete-Time Analysis

Beyond Bradley-Terry Models: A General Preference Model for Language Model Alignment

CryoFM: A Flow-based Foundation Model for Cryo-EM Densities

Speeding Up Latent Variable Gaussian Graphical Model Estimation via Nonconvex Optimization

NeurIPS 2017arXiv

Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models

Borda Regret Minimization for Generalized Linear Dueling Bandits

Towards Robust Model-Based Reinforcement Learning Against Adversarial Corruption

Uncertainty-Aware Reward-Free Exploration with General Function Approximation

Feel-Good Thompson Sampling for Contextual Dueling Bandits

LLaVA-Critic: Learning to Evaluate Multimodal Models

Diffusion Language Models Are Versatile Protein Learners

Protein Conformation Generation via Force-Guided SE(3) Diffusion Models

Position: TrustLLM: Trustworthiness in Large Language Models

High Dimensional EM Algorithm: Statistical Optimization and Asymptotic Normality

Exploring Architectural Ingredients of Adversarially Robust Deep Neural Networks

Do Wider Neural Networks Really Help Adversarial Robustness?

Variance-Aware Off-Policy Evaluation with Linear Function Approximation

Proxy Convexity: A Unified Framework for the Analysis of Neural Networks Trained by Gradient Descent

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

Pure Exploration in Kernel and Neural Bandits

Provably Efficient Reinforcement Learning with Linear Function Approximation under Adaptivity Constraints

Uniform-PAC Bounds for Reinforcement Learning with Linear Function Approximation

Nearly Minimax Optimal Reinforcement Learning for Discounted MDPs

Iterative Teacher-Aware Learning

NeurIPS 2021arXiv

Active Ranking without Strong Stochastic Transitivity

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

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

Towards Understanding the Mixture-of-Experts Layer in Deep Learning

Benign Overfitting in Two-layer Convolutional Neural Networks

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

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

Nearly Optimal Algorithms for Linear Contextual Bandits with Adversarial Corruptions

Computationally Efficient Horizon-Free Reinforcement Learning for Linear Mixture MDPs

Robust Learning with Progressive Data Expansion Against Spurious Correlation

Implicit Bias of Gradient Descent for Two-layer ReLU and Leaky ReLU Networks on Nearly-orthogonal Data

Optimal Extragradient-Based Algorithms for Stochastic Variational Inequalities with Separable Structure

Corruption-Robust Offline Reinforcement Learning with General Function Approximation

Why Does Sharpness-Aware Minimization Generalize Better Than SGD?

Towards a Lower Sample Complexity for Robust One-bit Compressed Sensing

On the Statistical Limits of Convex Relaxations

Towards Faster Rates and Oracle Property for Low-Rank Matrix Estimation

Uncertainty Assessment and False Discovery Rate Control in High-Dimensional Granger Causal Inference

Robust Gaussian Graphical Model Estimation with Arbitrary Corruption

A Unified Variance Reduction-Based Framework for Nonconvex Low-Rank Matrix Recovery

High-Dimensional Variance-Reduced Stochastic Gradient Expectation-Maximization Algorithm

Covariate Adjusted Precision Matrix Estimation via Nonconvex Optimization

Continuous and Discrete-time Accelerated Stochastic Mirror Descent for Strongly Convex Functions

Fast and Sample Efficient Inductive Matrix Completion via Multi-Phase Procrustes Flow

A Primal-Dual Analysis of Global Optimality in Nonconvex Low-Rank Matrix Recovery

Stochastic Variance-Reduced Cubic Regularized Newton Methods

Stochastic Variance-Reduced Hamilton Monte Carlo Methods

On the Convergence and Robustness of Adversarial Training

Lower Bounds for Smooth Nonconvex Finite-Sum Optimization

Stochastic Nested Variance Reduction for Nonconvex Optimization

Distributed Learning without Distress: Privacy-Preserving Empirical Risk Minimization

Global Convergence of Langevin Dynamics Based Algorithms for Nonconvex Optimization

Third-order Smoothness Helps: Faster Stochastic Optimization Algorithms for Finding Local Minima

Tight Sample Complexity of Learning One-hidden-layer Convolutional Neural Networks

An Improved Analysis of Training Over-parameterized Deep Neural Networks

Algorithm-Dependent Generalization Bounds for Overparameterized Deep Residual Networks

Layer-Dependent Importance Sampling for Training Deep and Large Graph Convolutional Networks

Stochastic Gradient Hamiltonian Monte Carlo Methods with Recursive Variance Reduction

Generalization Bounds of Stochastic Gradient Descent for Wide and Deep Neural Networks

Agnostic Learning of a Single Neuron with Gradient Descent

A Generalized Neural Tangent Kernel Analysis for Two-layer Neural Networks

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

NeurIPS 2020arXiv

Reward-Free Model-Based Reinforcement Learning with Linear Function Approximation

The Benefits of Implicit Regularization from SGD in Least Squares Problems