FLAML: A Fast and Lightweight AutoML Library

TL;DR

FLAML is a lightweight AutoML library that efficiently automates model and hyperparameter selection with minimal computational resources, outperforming existing solutions on benchmark tasks.

Contribution

The paper introduces FLAML, a novel AutoML library that combines simple search strategies into an adaptive system for low-cost, high-accuracy model optimization.

Findings

FLAML outperforms top AutoML libraries on benchmark datasets.

It achieves comparable or better accuracy with significantly less computational budget.

The library is fast, lightweight, and effective for resource-constrained environments.

Abstract

We study the problem of using low computational cost to automate the choices of learners and hyperparameters for an ad-hoc training dataset and error metric, by conducting trials of different configurations on the given training data. We investigate the joint impact of multiple factors on both trial cost and model error, and propose several design guidelines. Following them, we build a fast and lightweight library FLAML which optimizes for low computational resource in finding accurate models. FLAML integrates several simple but effective search strategies into an adaptive system. It significantly outperforms top-ranked AutoML libraries on a large open source AutoML benchmark under equal, or sometimes orders of magnitude smaller budget constraints.