No AI summary available for this article.
Why It Matters
Quasi-Newton (QN) methods have long been among the most effective methods for large-scale unconstrained convex optimization.
Provenance
Discovered via ArXiv and published by ArXiv.
Key Claims
Original description
Quasi-Newton (QN) methods have long been among the most effective methods for large-scale unconstrained convex optimization. Two obstacles have limited their use in deep learning: non-convexity and enormous parameter sizes. We introduce SoftServe, a family of QN methods designed to overcome these obstacles without line searches or ad hoc curvature corrections. SoftServe derives positivedefinite curvature estimates from the variational objective of Berglund et al. (2025), even in the presence of negative curvature. We develop diagonal and Kroneckerfactored variants that preserve positive defini...
Discovered via ArXiv
Research papers and preprints from arXiv.
Publisher: arxiv.org
ID: http://arxiv.org/abs/2610.02182v1 · Indexed about 1 hour ago