Multi-step Planning for Automated Hyperparameter Optimization with OptFormer

TL;DR

This paper introduces a multi-step planning approach for hyperparameter optimization using the OptFormer model, which leverages Transformer-based autoregressive generation to improve efficiency and reduce complexity in automated HPO.

Contribution

It demonstrates how to implement multi-step planning with OptFormer, enhancing non-myopic hyperparameter optimization strategies through efficient, Transformer-based autoregressive methods.

Findings

Multi-step planning improves HPO efficiency.

OptFormer enables simple and effective rollouts for planning.

The approach reduces computational complexity in hyperparameter tuning.

Abstract

As machine learning permeates more industries and models become more expensive and time consuming to train, the need for efficient automated hyperparameter optimization (HPO) has never been more pressing. Multi-step planning based approaches to hyperparameter optimization promise improved efficiency over myopic alternatives by more effectively balancing out exploration and exploitation. However, the potential of these approaches has not been fully realized due to their technical complexity and computational intensity. In this work, we leverage recent advances in Transformer-based, natural-language-interfaced hyperparameter optimization to circumvent these barriers. We build on top of the recently proposed OptFormer which casts both hyperparameter suggestion and target function approximation as autoregressive generation thus making planning via rollouts simple and efficient. We conduct extensive exploration of different strategies for performing multi-step planning on top of the OptFormer model to highlight its potential for use in constructing non-myopic HPO strategies.