General Oracle Inequalities for Gibbs Posterior with Application to Ranking
General Oracle Inequalities for Gibbs Posterior with Application to Ranking
Aug 9, 2013 2841 views 
en-es
en
0.25
0.5
0.75
1.25
1.5
1.75
2
In this paper, we summarize some recent results in Li et al. (2012), which can be used to extend an important PAC-Bayesian approach, namely the Gibbs posterior, to study the nonadditive ranking risk. The methodology is based on assumption-free risk bounds and nonasymptotic oracle inequalities, which leads to nearly optimal convergence rates and optimal model selection to balance the approximation errors and the stochastic errors.