all AI news
A PAC-Bayes bound for deterministic classifiers. (arXiv:2209.02525v2 [stat.ML] UPDATED)
Oct. 27, 2022, 1:12 a.m. | Eugenio Clerico, George Deligiannidis, Benjamin Guedj, Arnaud Doucet
cs.LG updates on arXiv.org arxiv.org
We establish a disintegrated PAC-Bayesian bound, for classifiers that are
trained via continuous-time (non-stochastic) gradient descent. Contrarily to
what is standard in the PAC-Bayesian setting, our result applies to a training
algorithm that is deterministic, conditioned on a random initialisation,
without requiring any $\textit{de-randomisation}$ step. We provide a broad
discussion of the main features of the bound that we propose, and we study
analytically and empirically its behaviour on linear models, finding promising
results.
More from arxiv.org / cs.LG updates on arXiv.org
Jobs in AI, ML, Big Data
Senior ML Researcher - 3D Geometry Processing | 3D Shape Generation | 3D Mesh Data
@ Promaton | Europe
Senior Manager, IT Ops & Service Management, AI/ML
@ Sephora | San Francisco, CA, US, 50302863
AI/ML Senior Software Engineer (Indonesia)
@ Bjak | Jakarta, Jakarta, Indonesia
Data Engineer
@ Accenture Federal Services | Laurel, MD
Principal Engineer, Deep Learning
@ Outrider | Montreal, Quebec
Consultant Data manager F/H
@ Atos | Bezons, FRANCE, FR, 95870