Multiclass Boosting: Simple and Intuitive Weak Learning Criteria

Nataly Brukhim, Amit Daniely, Yishay Mansour, Shay Moran

Research output: Contribution to journalConference articlepeer-review

Abstract

We study a generalization of boosting to the multiclass setting. We introduce a weak learning condition for multiclass classification that captures the original notion of weak learnability as being “slightly better than random guessing”. We give a simple and efficient boosting algorithm, that does not require realizability assumptions and its sample and oracle complexity bounds are independent of the number of classes. In addition, we utilize our new boosting technique in several theoretical applications within the context of List PAC Learning. First, we establish an equivalence to weak PAC learning. Furthermore, we present a new result on boosting for list learners, as well as provide a novel proof for the characterization of multiclass PAC learning and List PAC learning. Notably, our technique gives rise to a simplified analysis, and also implies an improved error bound for large list sizes, compared to previous results.

Original languageEnglish
JournalAdvances in Neural Information Processing Systems
Volume36
StatePublished - 2023
Event37th Conference on Neural Information Processing Systems, NeurIPS 2023 - New Orleans, United States
Duration: 10 Dec 202316 Dec 2023

Funding

FundersFunder number
Yandex Initiative for Machine Learning
NSF-Simons
Technion Center for Machine Learning and Intelligent Systems
MLIS
European Commission
European Research Executive Agency
Tel Aviv University
European Research Council
Iowa Science Foundation1225/20
Iowa Science Foundation
Israel Science Foundation2258/19
Israel Science Foundation
Bloom's Syndrome Foundation2018385
Bloom's Syndrome Foundation
European Union's Horizon 2022 research and innovation program101041711
GENERALIZATION101039692
Horizon 2020882396, 993/17
Horizon 2020

    Fingerprint

    Dive into the research topics of 'Multiclass Boosting: Simple and Intuitive Weak Learning Criteria'. Together they form a unique fingerprint.

    Cite this