all AI news
SAM as an Optimal Relaxation of Bayes. (arXiv:2210.01620v1 [cs.LG])
Oct. 5, 2022, 1:13 a.m. | Thomas Möllenhoff, Mohammad Emtiyaz Khan
stat.ML updates on arXiv.org arxiv.org
Sharpness-aware minimization (SAM) and related adversarial deep-learning
methods can drastically improve generalization, but their underlying mechanisms
are not yet fully understood. Here, we establish SAM as a relaxation of the
Bayes objective where the expected negative-loss is replaced by the optimal
convex lower bound, obtained by using the so-called Fenchel biconjugate. The
connection enables a new Adam-like extension of SAM to automatically obtain
reasonable uncertainty estimates, while sometimes also improving its accuracy.
By connecting adversarial and Bayesian methods, our work …
More from arxiv.org / stat.ML updates on arXiv.org
Jobs in AI, ML, Big Data
Senior ML Researcher - 3D Geometry Processing | 3D Shape Generation | 3D Mesh Data
@ Promaton | Europe
Data Architect
@ Western Digital | San Jose, CA, United States
Senior Data Scientist GenAI (m/w/d)
@ Deutsche Telekom | Bonn, Deutschland
Senior Data Engineer, Telco (Remote)
@ Lightci | Toronto, Ontario
Consultant Data Architect/Engineer H/F - Innovative Tech
@ Devoteam | Lyon, France
(Senior) ML Engineer / Software Engineer Machine Learning & AI (m/f/x) onsite or remote (in Germany or Austria)
@ Scalable GmbH | Wien, Germany