RESEARCH / SELECTED WORK

Publications & research.

Pre-training, first-order methods, and questions in reinforcement learning.

Publications

1 publication

NeurIPS2025

Accelerated Distance-adaptive Methods for Hölder Smooth and Convex Optimization

Yijin Ren, Haifeng Xu, Qi Deng

This paper proposes an adaptive, parameter-free accelerated method for local Hölder smooth convex optimization with optimal rates and no need for Lipschitz or target accuracy tuning.

Overview Paper

ON THE DESK

Ongoing work

IN PROGRESS

More in the making.

Projects in progress. Details will be shared here as they develop.