Additive Tree-Structured Conditional Parameter Spaces in Bayesian Optimization: A Novel Covariance Function and a Fast Implementation

TL;DR

This paper introduces a novel additive tree-structured covariance function for Bayesian optimization, enhancing sample efficiency and applicability in conditional parameter spaces, with a fast parallel implementation demonstrated on various benchmarks.

Contribution

It generalizes additive assumptions to tree-structured functions and develops a low-dimensional, parallel optimization algorithm for acquisition functions.

Findings

Outperforms state-of-the-art methods like SMAC, TPE, and Jenatton et al. (2017).

Shows improved sample efficiency and flexibility in conditional parameter optimization.

Successfully applied to neural network compression, pruning, and activation function search.

Abstract

Bayesian optimization (BO) is a sample-efficient global optimization algorithm for black-box functions which are expensive to evaluate. Existing literature on model based optimization in conditional parameter spaces are usually built on trees. In this work, we generalize the additive assumption to tree-structured functions and propose an additive tree-structured covariance function, showing improved sample-efficiency, wider applicability and greater flexibility. Furthermore, by incorporating the structure information of parameter spaces and the additive assumption in the BO loop, we develop a parallel algorithm to optimize the acquisition function and this optimization can be performed in a low dimensional space. We demonstrate our method on an optimization benchmark function, on a neural network compression problem, on pruning pre-trained VGG16 and ResNet50 models as well as on searching activation functions of ResNet20. Experimental results show our approach significantly outperforms the current state of the art for conditional parameter optimization including SMAC, TPE and Jenatton et al. (2017).