Polynomial learnability of stochastic rules with respect to the KL-divergence and quadratic distance

Naoki Abe, Junnichi Takeuchi, K. Manfred Warmuth

研究成果: Contribution to journalArticle査読

8 被引用数 (Scopus)

抄録

We consider the problem of efficient learning of probabilistic concepts (p-concepts) and more generally stochastic rules in the sense defined by Kearns and Schapire [6] and by Yamanishi [18]. Their models extend the PAC-learning model of Valiant [16] to the learning scenario in which the target concept or function is stochastic rather than deterministic as in Valiant's original model. In this paper, we consider the learnability of stochastic rules with respect to the classic 'Kullback-Leibler divergence' (KL divergence) as well as the quadratic distance as the distance measure between the rules. First, we show that the notion of polynomial time learnability of p-concepts and stochastic rules with fixed range size using the KL divergence is in fact equivalent to the same notion using the quadratic distance, and hence any of the distances considered in [6] and [18]: the quadratic, variation, and Hellinger distances. As a corollary, it follows that a wide range of classes of p-concepts which were shown to be polynomially learnable with respect to the quadratic distance in [6] are also learnable with respect to the KL divergence. The sample and time complexity of algorithms that would be obtained by the above general equivalence, however, are far from optimal. We present a polynomial learning algorithm with reasonable sample and time complexity for the important class of convex linear combinations of stochastic rules. We also develop a simple and versatile technique for obtaining sample complexity bounds for learning classes of stochastic rules with respect to the KL-divergence and quadratic distance, and apply them to produce bounds for the classes of probabilistic finite state acceptors (automata), probabilistic decision lists, and convex linear combinations.

本文言語英語
ページ(範囲)290-316
ページ数27
ジャーナルIEICE Transactions on Information and Systems
E84-D
3
出版ステータス出版済み - 2001
外部発表はい

All Science Journal Classification (ASJC) codes

  • Software
  • Hardware and Architecture
  • Computer Vision and Pattern Recognition
  • Electrical and Electronic Engineering
  • Artificial Intelligence

フィンガープリント 「Polynomial learnability of stochastic rules with respect to the KL-divergence and quadratic distance」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル