资源分类
》 资源 》论文》No-Regret Algorithms for Unconstrained Online Convex Optimization

No-Regret Algorithms for Unconstrained Online Convex Optimization

2020-01-13 | |  61 |   49 |   0

Abstract

Some of the most compelling applications of online convex optimization, including online prediction and classification, are unconstrained: the natural feasible set is 图片.png Existing algorithms fail to achieve sub-linear regret in this setting unless constraints on the comparator point 图片.png are known in advance. We present algorithms that, without such prior knowledge, offer near-optimal regret bounds with respect to any choice of 图片.png. In particular, regret with respect to 图片.png = 0 is constant. We then prove lower bounds showing that our guarantees are near-optimal in this setting.

上一篇：Scaled Gradients on Grassmann Manifolds for Matrix Completion

下一篇：Mandatory Leaf Node Prediction in Hierarchical Multilabel Classification

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...