A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Filters
A Tight Excess Risk Bound via a Unified PAC-Bayesian-Rademacher-Shtarkov-MDL Complexity
[article]
2017
arXiv
pre-print
Preserved Fulltext
Our first main result bounds excess risk in terms of the new complexity. ...
(also known as stochastic or PAC-Bayesian, KL(posteriorprior) complexity. ...
Problem C: Unifying data-dependent and empirical process-type excess risk bounds As lamented by Audibert (2004; 2009) , despite their considerable appeal, standard PAC-Bayesian and KL excess risk bounds ...
arXiv:1710.07732v1
fatcat:xifeif537fc4pfhnbtoshjfagq