资源分类
》 资源 》论文》Generalization Bounds and Consistency for Latent Structural Probit and Ramp Loss

Generalization Bounds and Consistency for Latent Structural Probit and Ramp Loss

2020-01-08 | |  68 |   37 |   0

Abstract

We consider latent structural versions of probit loss and ramp loss. We show that these surrogate loss functions are consistent in the strong sense that for any feature map (finite or infinite dimensional) they yield predictors approaching the infimum task loss achievable by any linear predictor over the given features. We also give finite sample generalization bounds (convergence rates) for these loss functions. These bounds suggest that probit loss converges more rapidly. However, ramp loss is more easily optimized on a given sample.

上一篇：Blending Autonomous Exploration and Apprenticeship Learning

下一篇：Analysis and Improvement of Policy Gradient Estimation

用户评价
全部评价

热门资源

  • Learning to Predi...

    Much of model-based reinforcement learning invo...

  • Stratified Strate...

    In this paper we introduce Stratified Strategy ...

  • The Variational S...

    Unlike traditional images which do not offer in...

  • A Mathematical Mo...

    Direct democracy, where each voter casts one vo...

  • Rating-Boosted La...

    The performance of a recommendation system reli...