Online and Batch Learning Algorithms for Data with Missing Features

TL;DR

This paper presents novel online and batch algorithms designed to handle data with missing features, improving robustness and performance in practical applications with incomplete data.

Contribution

It introduces the first algorithms that adapt to missing features in both online and batch learning, with theoretical guarantees and empirical validation.

Findings

Algorithms outperform baselines on UCI datasets.

Regret bounds established for online algorithms.

Rademacher complexity bounds for batch setting.

Abstract

We introduce new online and batch algorithms that are robust to data with missing features, a situation that arises in many practical applications. In the online setup, we allow for the comparison hypothesis to change as a function of the subset of features that is observed on any given round, extending the standard setting where the comparison hypothesis is fixed throughout. In the batch setup, we present a convex relation of a non-convex problem to jointly estimate an imputation function, used to fill in the values of missing features, along with the classification hypothesis. We prove regret bounds in the online setting and Rademacher complexity bounds for the batch i.i.d. setting. The algorithms are tested on several UCI datasets, showing superior performance over baselines.