Multi-armed bandits for resource efficient, online optimization of language model pre-training: the use case of dynamic masking

TL;DR

This paper introduces a Bayesian optimization framework using multi-armed bandits and Gaussian processes to efficiently select hyperparameters during language model pre-training, reducing computational costs and improving performance.

Contribution

It presents a novel Thompson sampling approach with Gaussian process modeling for dynamic hyperparameter selection in TLM pre-training, avoiding costly grid searches.

Findings

GP-TS accelerates pre-training by reducing epochs needed.

Achieves lower MLM loss compared to fixed hyperparameters.

Attains competitive downstream performance.

Abstract

We design and evaluate a Bayesian optimization framework for resource efficient pre-training of Transformer-based language models (TLMs). TLM pre-training requires high computational resources and introduces many unresolved design choices, such as selecting its pre-training hyperparameters. We propose a multi-armed bandit framework for the sequential selection of TLM pre-training hyperparameters, aimed at optimizing language model performance, in a resource efficient manner. We design a Thompson sampling algorithm, with a surrogate Gaussian process reward model of the Masked Language Model (MLM) pre-training objective, for its sequential minimization. Instead of MLM pre-training with fixed masking probabilities, the proposed Gaussian process-based Thompson sampling (GP-TS) accelerates pre-training by sequentially selecting masking hyperparameters that improve performance. We empirically demonstrate how GP-TS pre-trains language models efficiently, i.e., it achieves lower MLM loss in fewer epochs, across a variety of settings. In addition, GP-TS pre-trained TLMs attain competitive downstream performance, while avoiding expensive hyperparameter grid search. GP-TS provides an interactive framework for efficient and optimized TLM pre-training that, by circumventing costly hyperparameter selection, enables substantial computational savings.