资源分类
》 资源 》论文》Following the Perturbed Leader for Online Structured Learning

Following the Perturbed Leader for Online Structured Learning

2020-03-05 | |  95 |   58 |   0

Abstract

We investigate a new Follow the Perturbed Leader (FTPL) algorithm for online structured prediction problems. We show a regret bound which is comparable to the state of the art of FTPL algorithms and is comparable with the best possible regret in some cases. To better understand FTPL algorithms for online structured learning, we present a lower bound on the regret for a large and natural class of FTPL algorithms that use logconcave perturbations. We complete our investigation with an online shortest path experiment and empirically show that our algorithm is both statistically and computationally efficient.

上一篇：A General Analysis of the Convergence of ADMM

下一篇：Non-Gaussian Discriminative Factor Models via the Max-Margin Rank-Likelihood

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...