Yudong Chen

22

Papers

296

Total Citations

Papers (22)

Fast Algorithms for Robust PCA via Gradient Descent

NeurIPS 2016arXiv

Soft Reasoning: Navigating Solution Spaces in Large Language Models through Controlled Embedding Exploration

LoRA-One: One-Step Full Gradient Could Suffice for Fine-Tuning Large Language Models, Provably and Efficiently

Effectiveness of Constant Stepsize in Markovian LSA and Statistical Inference

Stable Offline Value Function Learning with Bisimulation-based Representations

Medium-Difficulty Samples Constitute Smoothed Decision Boundary for Knowledge Distillation on Pruned Datasets

The $\varphi$ Curve: The Shape of Generalization through the Lens of Norm-based Capacity Control

Learning to Stabilize Online Reinforcement Learning in Unbounded State Spaces

Minimally Modifying a Markov Game to Achieve Any Nash Equilibrium and Value

Tensor Robust Principal Component Analysis: Exact Recovery of Corrupted Low-Rank Tensors via Convex Optimization

Deep Supervised Hashing With Anchor Graph

Defending Against Saddle Point Attack in Byzantine-Robust Distributed Learning

Factor Group-Sparse Regularization for Efficient Low-Rank Matrix Recovery

Global Convergence of Least Squares EM for Demixing Two Log-Concave Densities

Risk-Sensitive Reinforcement Learning: Near-Optimal Risk-Sample Tradeoff in Regret

Exponential Bellman Equation and Improved Regret Bounds for Risk-Sensitive Reinforcement Learning

Rank Overspecified Robust Matrix Recovery: Subgradient Method and Exact Recovery

Curriculum Disentangled Recommendation with Noisy Multi-feedback

Improved Feature Distillation via Projector Ensemble

Restless Bandits with Average Reward: Breaking the Uniform Global Attractor Assumption

A Convex Optimization Framework for Bi-Clustering

Byzantine-Robust Distributed Learning: Towards Optimal Statistical Rates