资源分类
》 资源 》论文》Tight Sample Complexity of Large-Margin Learning

Tight Sample Complexity of Large-Margin Learning

2020-01-06 | |  96 |   95 |   0

Abstract

We obtain a tight distribution-specific characterization of the sample complexity of large-margin classification with 图片.png regularization: We introduce the 图片.png-adapted-dimension, which is a simple function of the spectrum of a distribution’s covariance matrix, and show distribution-specific upper and lower bounds on the sample complexity, both governed by the 图片.png-adapted-dimension of the source distribution. We conclude that this new quantity tightly characterizes the true sample complexity of large-margin classification. The bounds hold for a rich family of sub-Gaussian distributions.

上一篇：New Adaptive Algorithms for Online Classification

下一篇：A Reduction from Apprenticeship Learning to Classification

用户评价
全部评价

热门资源

  • Deep Cross-media ...

    Cross-media retrieval is a research hotspot in ...

  • Regularizing RNNs...

    Recently, caption generation with an encoder-de...

  • The Variational S...

    Unlike traditional images which do not offer in...

  • Joint Pose and Ex...

    Facial expression recognition (FER) is a challe...

  • Visual Reinforcem...

    For an autonomous agent to fulfill a wide range...