Yasong Feng

A Lipschitz Bandits Approach for Continuous Hyperparameter Optimization

2023 · arXiv (Cornell University)

One of the most critical problems in machine learning is HyperParameter Optimization (HPO), since choice of hyperparameters has a significant impact on final model performance. Although there are many HPO algorithms, they either have no …

Breaking a Logarithmic Barrier in the Stopping Time Convergence Rate of Stochastic First-order Methods

2025 · arXiv (Cornell University)

This work provides a novel convergence analysis for stochastic optimization in terms of stopping times, addressing the practical reality that algorithms are often terminated adaptively based on observed progress. Unlike prior approaches, our analysis: 1. …