Dingzhi Yu

2 accepted papers

2026

Mirror Descent Under Generalized Smoothness

Dingzhi Yu, Wei Jiang, Hongyi Tao, Yuanyu Wan, Lijun Zhang

ICML 2026poster

Smoothness is crucial for attaining fast rates in first-order optimization. However, many optimization problems in modern machine learning involve non-smooth objectives. Recent studies relax the smoothness assumption by allowing the Lipschitz constant of the gradient to grow with respect to the grad…

Cited by 0 Source ↗Scholar ↗

2024

Efficient Algorithms for Empirical Group Distributionally Robust Optimization and Beyond

Dingzhi Yu, Yunuo Cai, Wei Jiang, Lijun Zhang

ICML 2024poster

In this paper, we investigate the empirical counterpart of Group Distributionally Robust Optimization (GDRO), which aims to minimize the maximal empirical risk across $m$ distinct groups. We formulate empirical GDRO as a *two-level* finite-sum convex-concave minimax optimization problem and develop…

Cited by 7 Source ↗PDF ↗Scholar ↗