3 papers
math.OC2026
New Results on the Polyak Stepsize: Tight Convergence Analysis and Universal Function Classes
Chang He, Wenzhi Gao, Bo Jiang +2
In this paper, we revisit a classical adaptive stepsize strategy for gradient descent: the Polyak stepsize (PolyakGD), originally proposed in Polyak (1969). We study the convergenc…
stat.ML2026
Small Gradient Norm Regret for Online Convex Optimization
Wenzhi Gao, Chang He, Madeleine Udell
This paper introduces a new problem-dependent regret measure for online convex optimization with smooth losses. The notion, which we call the regret, depends on the cumul…
cs.DS2025
Revoke vs. Restart in Unweighted Throughput Scheduling
Changdao He
We study the unweighted throughput scheduling problem on a single machine in the preemption-revoke model, where a running job may be aborted at any time, but all progress is perman…