all AI news
Inexact subgradient methods for semialgebraic functions
May 1, 2024, 4:46 a.m. | J\'er\^ome Bolte (TSE-R), Tam Le (UGA, LJK), \'Eric Moulines (CMAP, MBZUAI), Edouard Pauwels (TSE-R, IUF)
stat.ML updates on arXiv.org arxiv.org
Abstract: Motivated by the widespread use of approximate derivatives in machine learning and optimization, we study inexact subgradient methods with non-vanishing additive errors and step sizes. In the nonconvex semialgebraic setting, under boundedness assumptions, we prove that the method provides points that eventually fluctuate close to the critical set at a distance proportional to $\epsilon^\rho$ where $\epsilon$ is the error in subgradient evaluation and $\rho$ relates to the geometry of the problem. In the convex setting, …
abstract arxiv assumptions derivatives errors eventually functions machine machine learning math.oc optimization prove set stat.ml study type
More from arxiv.org / stat.ML updates on arXiv.org
Jobs in AI, ML, Big Data
Software Engineer for AI Training Data (School Specific)
@ G2i Inc | Remote
Software Engineer for AI Training Data (Python)
@ G2i Inc | Remote
Software Engineer for AI Training Data (Tier 2)
@ G2i Inc | Remote
Data Engineer
@ Lemon.io | Remote: Europe, LATAM, Canada, UK, Asia, Oceania
Artificial Intelligence – Bioinformatic Expert
@ University of Texas Medical Branch | Galveston, TX
.NET Software Engineer (AI Focus)
@ Boskalis | Papendrecht, Netherlands