Expert advice problem with noisy low rank lossDownload PDFOpen Website

2021 (modified: 24 Apr 2023)ACML 2021Readers: Everyone
Abstract: We consider the expert advice problem with a low rank but noisy loss sequence, where a loss vector $l_{t} \in [-1,1]^N$ in each round $t$ is of the form $l_{t} = U v_{t} + \epsilon_{t}$ for some fi...
0 Replies

Loading