Online Agnostic Multiclass Boosting

TL;DR

This paper introduces the first online agnostic multiclass boosting algorithm, extending existing binary boosting methods to handle multiple classes and various learning settings through a novel reduction to online convex optimization.

Contribution

It extends the reduction approach from binary to multiclass boosting, enabling new algorithms for multiple learning scenarios.

Findings

First online agnostic multiclass boosting algorithm

Supports statistical and online realizable settings

Builds on reduction to online convex optimization

Abstract

Boosting is a fundamental approach in machine learning that enjoys both strong theoretical and practical guarantees. At a high-level, boosting algorithms cleverly aggregate weak learners to generate predictions with arbitrarily high accuracy. In this way, boosting algorithms convert weak learners into strong ones. Recently, Brukhim et al. extended boosting to the online agnostic binary classification setting. A key ingredient in their approach is a clean and simple reduction to online convex optimization, one that efficiently converts an arbitrary online convex optimizer to an agnostic online booster. In this work, we extend this reduction to multiclass problems and give the first boosting algorithm for online agnostic mutliclass classification. Our reduction also enables the construction of algorithms for statistical agnostic, online realizable, and statistical realizable multiclass boosting.