资源分类
》 资源 》论文》On the Spectrum of Random Features Maps of High Dimensional Data

On the Spectrum of Random Features Maps of High Dimensional Data

2020-03-11 | |  55 |   37 |   0

Abstract

Random feature maps are ubiquitous in modern statistical machine learning, where they generalize random projections by means of powerful, yet often difficult to analyze nonlinear operators. In this paper, we leverage the “concentration” phenomenon induced by random matrix theory to perform a spectral analysis on the Gram matrix of these random feature maps, here for Gaussian mixture models of simultaneously large dimension and size. Our results are instrumental to a deeper understanding on the interplay of the nonlinearity and the statistics of the data, there allowing for a better tuning of random featurebased techniques.

上一篇：Augment and Reduce: Stochastic Inference for Large Categorical Distributions

下一篇：Model-Level Dual Learning

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...