all AI news
More PAC-Bayes bounds: From bounded losses, to losses with general tail behaviors, to anytime-validity
Feb. 15, 2024, 5:43 a.m. | Borja Rodr\'iguez-G\'alvez, Ragnar Thobaben, Mikael Skoglund
cs.LG updates on arXiv.org arxiv.org
Abstract: In this paper, we present new high-probability PAC-Bayes bounds for different types of losses. Firstly, for losses with a bounded range, we recover a strengthened version of Catoni's bound that holds uniformly for all parameter values. This leads to new fast rate and mixed rate bounds that are interpretable and tighter than previous bounds in the literature. In particular, the fast rate bound is equivalent to the Seeger--Langford bound. Secondly, for losses with more general …
abstract arxiv bayes cs.lg general leads losses paper probability stat.ml type types values
More from arxiv.org / cs.LG updates on arXiv.org
Jobs in AI, ML, Big Data
Lead Developer (AI)
@ Cere Network | San Francisco, US
Research Engineer
@ Allora Labs | Remote
Ecosystem Manager
@ Allora Labs | Remote
Founding AI Engineer, Agents
@ Occam AI | New York
AI Engineer Intern, Agents
@ Occam AI | US
AI Research Scientist
@ Vara | Berlin, Germany and Remote