Hoi To Wai

A Stochastic Approximation Approach for Efficient Decentralized Optimization on Random Networks

Clipped SGD Algorithms for Performative Prediction: Tight Bounds for Stochastic Bias and Remedies

RoSTE: An Efficient Quantization-Aware Supervised Fine-Tuning Approach for Large Language Models

Incremental Aggregated Asynchronous SGD for Arbitrarily Heterogeneous Data

Stochastic Optimization Schemes for Performative Prediction with Nonconvex Loss

Getting More Juice Out of the SFT Data: Reward Learning from Human Demonstration Improves SFT for LLM Alignment