We disprove a conjecture of Davis, Drusvyatskiy, and Jiang (2026) that subdifferential regularity can be removed from the generic guarantee of convergence to local minimizers for stochastic subgradient methods. We construct a globally Lipschitz, coercive, semialgebraic function in two dimensions for which the method co...
Scaling deep learning models efficiently requires predictable performance transfer across compute regimes. Establishing reliable hyperparameter transfer allows optimal training dynamics and structural choices to be discovered on low-cost proxy models, avoiding catastrophic failures during massive-scale training. Existi...
Maximilian Wong, Chen-Yu Xu, Jia-Jin Li et al.· 0 citations
This paper establishes last-iterate convergence of stochastic first-order methods for constrained smooth convex--concave minimax optimization under the standard bounded-variance stochastic oracle and establishes two types of convergence guarantees.
Tao-Li Zheng, Jiajin Li, Anthony Man-Cho So· 1 citation· ⚡1
The main contribution is a finite-time mechanism for converting stationarity of the truncated minimax problem into a KKT certificate for the original constrained problem and establishing explicit convergence rates for the proposed method in terms of the KKT residual.
Lingling Zhu, Jiajin Li· 2 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.