Zobrazeno 1 - 3
of 3
pro vyhledávání: '"Koolen, W. M."'
For every total recursive time bound $t$, a constant fraction of all compressible (low Kolmogorov complexity) strings is $t$-bounded incompressible (high time-bounded Kolmogorov complexity); there are uncountably many infinite sequences of which ever
Externí odkaz:
http://arxiv.org/abs/0809.2965
Publikováno v:
Scopus-Elsevier
Journal of Machine Learning Research, 22, 1-61
Journal of Machine Learning Research, 22, 1-61
We provide a new adaptive method for online convex optimization, MetaGrad, that is ro- bust to general convex losses but achieves faster rates for a broad class of special functions, including exp-concave and strongly convex functions, but also vario
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::75003f071aa085e9c7a190035fbe1eea
Publikováno v:
Scopus-Elsevier
Most methods for decision-theoretic online learning are based on the Hedge algorithm, which takes a parameter called the learning rate. In most previous analyses the learning rate was carefully tuned to obtain optimal worst-case performance, leading
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::852c9188a91826075678f4c3c47b2a17
http://arxiv.org/abs/1110.6416
http://arxiv.org/abs/1110.6416