资源分类
》 资源 》论文》An Online Learning Algorithm for Bilinear Models

An Online Learning Algorithm for Bilinear Models

2020-03-05 | |  48 |   43 |   0

Abstract

We investigate the bilinear model, which is a matrix form linear model with the rank 1 constraint. A new online learning algorithm is proposed to train the model parameters. Our algorithm runs in the manner of online mirror descent, and gradients are computed by the power iteration. To analyze it, we give a new second order approximation of the squared spectral norm, which helps us to get a regret bound. Experiments on two sequential labelling tasks give positive results.

上一篇：Statistical and Algorithmic Perspectives on Randomized Sketching for Ordinary Least-Squares

下一篇：Faster Cover Trees

用户评价
全部评价

热门资源

  • The Variational S...

    Unlike traditional images which do not offer in...

  • Learning to Predi...

    Much of model-based reinforcement learning invo...

  • Stratified Strate...

    In this paper we introduce Stratified Strategy ...

  • A Mathematical Mo...

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

  • Rating-Boosted La...

    The performance of a recommendation system reli...