# DEEP-BO for Hyperparameter Optimization of Deep Networks

## TL;DR

DEEP-BO is a specialized Bayesian optimization algorithm designed to efficiently tune hyperparameters of deep neural networks, outperforming or matching existing methods across multiple benchmarks.

## Contribution

The paper introduces DEEP-BO, a novel hyperparameter optimization method tailored for deep networks, incorporating diversification, early stopping, and parallelization strategies.

## Key findings

- DEEP-BO outperforms several existing hyperparameter optimization methods.
- DEEP-BO achieves comparable results with state-of-the-art solutions.
- The approach is validated on six deep learning benchmarks.

## Abstract

The performance of deep neural networks (DNN) is very sensitive to the particular choice of hyper-parameters. To make it worse, the shape of the learning curve can be significantly affected when a technique like batchnorm is used. As a result, hyperparameter optimization of deep networks can be much more challenging than traditional machine learning models. In this work, we start from well known Bayesian Optimization solutions and provide enhancement strategies specifically designed for hyperparameter optimization of deep networks. The resulting algorithm is named as DEEP-BO (Diversified, Early-termination-Enabled, and Parallel Bayesian Optimization). When evaluated over six DNN benchmarks, DEEP-BO easily outperforms or shows comparable performance with some of the well-known solutions including GP-Hedge, Hyperband, BOHB, Median Stopping Rule, and Learning Curve Extrapolation. The code used is made publicly available at https://github.com/snu-adsl/DEEP-BO.