Selecting Near-Optimal Learners via Incremental Data Allocation

TL;DR

This paper introduces DAUB, a new method for efficiently allocating small data subsets among classifiers to select near-optimal models with minimal misallocation costs, supported by theoretical and empirical evidence.

Contribution

The paper proposes DAUB, an innovative data allocation strategy that balances accuracy and cost, with theoretical guarantees and practical effectiveness demonstrated on real datasets.

Findings

DAUB effectively identifies near-optimal classifiers with minimal data misallocation.

Theoretical bounds on regret and suboptimality are established for idealized scenarios.

Empirical results suggest DAUB performs well in real-world applications.

Abstract

We study a novel machine learning (ML) problem setting of sequentially allocating small subsets of training data amongst a large set of classifiers. The goal is to select a classifier that will give near-optimal accuracy when trained on all data, while also minimizing the cost of misallocated samples. This is motivated by large modern datasets and ML toolkits with many combinations of learning algorithms and hyper-parameters. Inspired by the principle of "optimism under uncertainty," we propose an innovative strategy, Data Allocation using Upper Bounds (DAUB), which robustly achieves these objectives across a variety of real-world datasets. We further develop substantial theoretical support for DAUB in an idealized setting where the expected accuracy of a classifier trained on $n$ samples can be known exactly. Under these conditions we establish a rigorous sub-linear bound on the regret of the approach (in terms of misallocated data), as well as a rigorous bound on suboptimality of the selected classifier. Our accuracy estimates using real-world datasets only entail mild violations of the theoretical scenario, suggesting that the practical behavior of DAUB is likely to approach the idealized behavior.