Xuyang Wu

Optimal convergence rates of totally asynchronous optimization

2022 · arXiv (Cornell University)

Asynchronous optimization algorithms are at the core of modern machine learning and resource allocation systems. However, most convergence results consider bounded information delays and several important algorithms lack guarantees when they operate under total asynchrony. …

A Survey on Feedback-based Multi-step Reasoning for Large Language Models on Mathematics

2025 · arXiv (Cornell University)

Recent progress in large language models (LLM) found chain-of-thought prompting strategies to improve the reasoning ability of LLMs by encouraging problem solving through multiple steps. Therefore, subsequent research aimed to integrate the multi-step reasoning process …