arXiv Machine Learning By Kuangyu Ding, Kim-Chuan Toh

Non-KKT Accumulation in Entropic Mirror Descent

Read the original on arXiv Machine Learning →

arXiv:2608. 01658v1 Announce Type: cross Abstract: For mirror descent generated by a Legendre kernel, perhaps one of the most basic question in optimization is this: must every accumulation point of a bounded mirror descent sequence be Karush--Kuhn--Tucker (KKT) stationary under proper stepsizes?

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv Machine Learning
Jul 21

Scaling Limits of Constant-Stepsize SGD at Flat Minima

arXiv:2607. 16384v1 Announce Type: new Abstract: For stochastic gradient descent (SGD) with a constant stepsize $\alpha$, the invariant law of the iterates, centered at a minimizer, describes the behavior of the algorithm over long time horizons.

By Jingyi Zhang, Cheng Mao, Debankur Mukherjee
arXiv Machine Learning
Aug 10

A proximal subgradient method for nonconvex stochastic optimization under the Kurdyka-{\L}ojasiewicz condition

arXiv:2608. 05460v1 Announce Type: cross Abstract: This work introduces a proximal stochastic subgradient method for minimizing the sum of an expected cost, whose integrand is potentially nonsmooth and nonconvex, and a lower semicontinuous, prox-bounded function.

By Felipe Atenas, Alejandro Jofr\'e, Pedro P\'erez-Aros, David Torregrosa-Bel\'en
arXiv Machine Learning
Jun 11

Mirror Descent Beyond Euclidean Stability: An Exponential Separation in Initialization Sensitivity

arXiv:2606. 11431v1 Announce Type: new Abstract: Mirror Descent (MD) extends Gradient Descent (GD) beyond Euclidean geometry and has recently reappeared as a lens for KL-regularized policy optimization in reinforcement learning and LLM post-training.

By Shira Vansover-Hager, Matan Schliserman, Ofir Schlisselberg, Tomer Koren