PAC-Bayes under potentially heavy tails
| 
48 | 
30 | 
0
Abstract
We derive PAC-Bayesian learning guarantees for heavy-tailed losses, and obtain a novel optimal Gibbs posterior which enjoys finite-sample excess risk bounds at logarithmic confidence. Our core technique itself makes use of PAC-Bayesian inequalities in order to derive a robust risk estimator, which by design is easy to compute. In particular, only assuming that the first three moments of the loss distribution are bounded, the learning algorithm derived from this estimator achieves nearly sub-Gaussian statistical error, up to the quality of the prior.
还没有评论，说两句吧！
热门资源
Stratified Strate...
In this paper we introduce Stratified Strategy ...
The Variational S...
Unlike traditional images which do not offer in...
Learning to learn...
The move from hand-designed features to learned...
A Mathematical Mo...
Direct democracy, where each voter casts one vo...
Learning to Predi...
Much of model-based reinforcement learning invo...
智能在线
400-630-6780
聆听.建议反馈
E-mail: support@tusaishared.com
资源分类
