papers AI Learner
The Github is limit! Click to go to the new site.

Generalization in Machine Learning via Analytical Learning Theory

2019-03-06
Kenji Kawaguchi, Yoshua Bengio, Vikas Verma, Leslie Pack Kaelbling

Abstract

This paper introduces a novel measure-theoretic theory for machine learning that does not require statistical assumptions. Based on this theory, a new regularization method in deep learning is derived and shown to outperform previous methods in CIFAR-10, CIFAR-100, and SVHN. Moreover, the proposed theory provides a theoretical basis for a family of practically successful regularization methods in deep learning. We discuss several consequences of our results on one-shot learning, representation learning, deep learning, and curriculum learning. Unlike statistical learning theory, the proposed learning theory analyzes each problem instance individually via measure theory, rather than a set of problem instances via statistics. As a result, it provides different types of results and insights when compared to statistical learning theory.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1802.07426

PDF

http://arxiv.org/pdf/1802.07426


Similar Posts

Comments