Neighbor Regularized Bayesian Optimization for Hyperparameter Optimization

TL;DR

This paper introduces Neighbor Regularized Bayesian Optimization (NRBO), a novel approach that enhances hyperparameter tuning by smoothing observations and adjusting acquisition rewards based on sample density, leading to more stable and efficient optimization.

Contribution

The paper proposes a neighbor-based regularization and a density-aware acquisition function for Bayesian Optimization, improving convergence speed and robustness against observation noise.

Findings

NRBO outperforms state-of-the-art methods on benchmark datasets.

The neighbor regularization reduces observation noise effectively.

Density-based adjustments improve stability and convergence.

Abstract

Bayesian Optimization (BO) is a common solution to search optimal hyperparameters based on sample observations of a machine learning model. Existing BO algorithms could converge slowly even collapse when the potential observation noise misdirects the optimization. In this paper, we propose a novel BO algorithm called Neighbor Regularized Bayesian Optimization (NRBO) to solve the problem. We first propose a neighbor-based regularization to smooth each sample observation, which could reduce the observation noise efficiently without any extra training cost. Since the neighbor regularization highly depends on the sample density of a neighbor area, we further design a density-based acquisition function to adjust the acquisition reward and obtain more stable statistics. In addition, we design a adjustment mechanism to ensure the framework maintains a reasonable regularization strength and density reward conditioned on remaining computation resources. We conduct experiments on the bayesmark benchmark and important computer vision benchmarks such as ImageNet and COCO. Extensive experiments demonstrate the effectiveness of NRBO and it consistently outperforms other state-of-the-art methods.