Learning Half-Spaces and other Concept Classes in the Limit with Iterative Learners

TL;DR

This paper explores the capabilities of iterative learning algorithms in concept learning, analyzing different settings and restrictions, and introduces a constructive method for learning half-spaces from informant data.

Contribution

It provides a detailed analysis of iterative learning power across various settings and presents a new constructive algorithm for learning half-spaces from informant.

Findings

Strongly non-U-shaped learning is restrictive for iterative learning from informant.

Iterative algorithms can learn the class of half-spaces from informant data.

Different learning settings have varying impacts on iterative learning capabilities.

Abstract

In order to model an efficient learning paradigm, iterative learning algorithms access data one by one, updating the current hypothesis without regress to past data. Past research on iterative learning analyzed for example many important additional requirements and their impact on iterative learners. In this paper, our results are twofold. First, we analyze the relative learning power of various settings of iterative learning, including learning from text and from informant, as well as various further restrictions, for example we show that strongly non-U-shaped learning is restrictive for iterative learning from informant. Second, we investigate the learnability of the concept class of half-spaces and provide a constructive iterative algorithm to learn the set of half-spaces from informant.