all AI news
A PAC-Bayes bound for deterministic classifiers. (arXiv:2209.02525v2 [stat.ML] UPDATED)
Oct. 27, 2022, 1:13 a.m. | Eugenio Clerico, George Deligiannidis, Benjamin Guedj, Arnaud Doucet
stat.ML 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 / stat.ML updates on arXiv.org
Jobs in AI, ML, Big Data
Data Architect
@ University of Texas at Austin | Austin, TX
Data ETL Engineer
@ University of Texas at Austin | Austin, TX
Lead GNSS Data Scientist
@ Lurra Systems | Melbourne
Senior Machine Learning Engineer (MLOps)
@ Promaton | Remote, Europe
Data Engineer
@ Parker | New York City
Sr. Data Analyst | Home Solutions
@ Three Ships | Raleigh or Charlotte, NC