Work

A Characterization of Multioutput Learnability

Year: 2023

Type: preprint

Abstract: We consider the problem of learning multioutput function classes in the batch and online settings. In both settings, we show that a multioutput function class is learnable if and only if each single-output restriction of the function class is learnable. This provides a complete characterization of the learnability of multilabel classification and multioutput regression in both batch and online settings. As an extension, we also consider multilabel learnability in the bandit feedback setting and show a similar characterization as in the full-feedback setting.

Source: arXiv (Cornell University)

DOI: 10.48550/arxiv.2301.02729

Authors: Raman, Vinod, Subedi, Unique, Tewari, Ambuj

Institution: University of Michigan

Language: English

Topic: Machine Learning and Algorithms

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

Funder: National Science Foundation

Awards: Learning Operators Between Infinite-Dimensional Hilbert Spaces, RI: Small: Random Perturbation Methods in Sequential Learning

OpenAlex ID: W4315588257

Cites:

Cited by:

Related to: 10