Picture for Xinmeng Huang

Xinmeng Huang

One-Shot Safety Alignment for Large Language Models via Optimal Dualization

Add code
May 29, 2024
Viaarxiv icon

Uncertainty in Language Models: Assessment through Rank-Calibration

Add code
Apr 04, 2024
Viaarxiv icon

Decentralized Bilevel Optimization over Graphs: Loopless Algorithmic Update and Transient Iteration Complexity

Add code
Feb 05, 2024
Viaarxiv icon

Stochastic Controlled Averaging for Federated Learning with Communication Compression

Add code
Aug 16, 2023
Viaarxiv icon

Momentum Benefits Non-IID Federated Learning Simply and Provably

Add code
Jun 28, 2023
Viaarxiv icon

Optimal Heterogeneous Collaborative Linear Regression and Contextual Bandits

Add code
Jun 09, 2023
Viaarxiv icon

Unbiased Compression Saves Communication in Distributed Optimization: When and How Much?

Add code
May 25, 2023
Viaarxiv icon

Lower Bounds and Accelerated Algorithms in Distributed Stochastic Optimization with Communication Compression

Add code
May 12, 2023
Viaarxiv icon

Demystifying Disagreement-on-the-Line in High Dimensions

Add code
Jan 31, 2023
Viaarxiv icon

Optimal Complexity in Non-Convex Decentralized Learning over Time-Varying Networks

Add code
Nov 01, 2022
Viaarxiv icon