conftrace_

2013 COLT COLT 2013

General Oracle Inequalities for Gibbs Posterior with Application to Ranking

Abstract

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.

🐣 Hot Topic Early Bird - model selection

Authors

Cheng Li, Wenxin Jiang, Martin Tanner

Topics

Machine Learning > Optimization & Theory > Bayesian Inference Machine Learning > Optimization & Theory > Learning Theory Machine Learning > Bayesian & Probabilistic > Bayesian Learning Machine Learning > Learning Types > Supervised Learning Machine Learning > Core Methods > Ranking

Keywords

model selection oracle inequalities oracle inequality pac-bayesian bound convergence rate gibbs posterior ranking risk

More from COLT 2013

All COLT 2013 papers →

Prediction by random-walk perturbation

Approachability, fast and slow

Classification with Asymmetric Label Noise: Consistency and Maximal Denoising

Learning Halfspaces Under Log-Concave Densities: Polynomial Approximations and Moment Matching

Subspace Embeddings and \ell_p-Regression Using Exponential Random Variables

Consistency of Robust Kernel Density Estimators