Universal Online Learning with Bounded Loss: Reduction to Binary ClassificationDownload PDFOpen Website

2022 (modified: 25 Apr 2023)COLT 2022Readers: Everyone
Abstract: We study universal consistency of non-i.i.d. processes in the context of online learning. A stochastic process is said to admit universal consistency if there exists a learner that achieves vanishi...
0 Replies

Loading