Tight Bounds on Minimax Regret under Logarithmic Loss via Self-ConcordanceDownload PDFOpen Website

2020 (modified: 14 Sept 2021)ICML 2020Readers: Everyone
Abstract: We consider the classical problem of sequential probability assignment under logarithmic loss while competing against an arbitrary, potentially nonparametric class of experts. We obtain tight bound...
0 Replies

Loading