arXiv Machine Learning By Jiseok Chae, Donghwan Kim

Understanding Schedule-Free Methods in Nonconvex Optimization: Rate Guarantees and Escaping Saddles

Read the original on arXiv Machine Learning →

arXiv:2607. 09167v1 Announce Type: new Abstract: Schedule-Free methods have attracted growing interest for alleviating the burden of designing and tuning a learning rate scheduler, while matching and sometimes even outperforming optimizers with tuned schedulers.

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

arXiv Machine Learning
Jun 16

Schattor: Schatten-family methods for deep learning optimization

arXiv:2606. 15702v1 Announce Type: cross Abstract: Modern deep learning optimization features heterogeneous parameter structures, noisy gradients, and highly nonconvex landscapes, posing significant challenges for both algorithm design and theoretical analysis.

By Bohao Ma, Junyu Zhang, Chuan He
arXiv Machine Learning
Jun 2

Safeguarded Stochastic Polyak Step Sizes for Non-smooth Optimization: Robust Performance Without Small (Sub)Gradients

arXiv:2512. 02342v3 Announce Type: replace-cross Abstract: The stochastic Polyak step size (SPS) has proven to be a promising choice for stochastic gradient descent (SGD), delivering competitive performance relative to state-of-the-art methods on smooth convex and non-convex optimization problems, including deep neural network training.

By Dimitris Oikonomou, Nicolas Loizou