Deakin University
Browse
- No file added yet -

Incorporating expert prior in Bayesian optimisation via space warping

Download (3.04 MB)
Version 4 2024-06-06, 01:32
Version 3 2024-02-09, 05:29
Version 2 2024-01-19, 04:25
Version 1 2020-03-16, 08:36
journal contribution
posted on 2024-06-06, 01:32 authored by A Ramachandran, Sunil GuptaSunil Gupta, Santu RanaSantu Rana, C Li, Svetha VenkateshSvetha Venkatesh
Bayesian optimisation is a well-known sample-efficient method for the optimisation of expensive black-box functions. However when dealing with big search spaces the algorithm goes through several low function value regions before reaching the optimum of the function. Since the function evaluations are expensive in terms of both money and time, it may be desirable to alleviate this problem. One approach to subside this cold start phase is to use prior knowledge that can accelerate the optimisation. In its standard form, Bayesian optimisation assumes the likelihood of any point in the search space being the optimum is equal. Therefore any prior knowledge that can provide information about the optimum of the function would elevate the optimisation performance. In this paper, we represent the prior knowledge about the function optimum through a prior distribution. The prior distribution is then used to warp the search space in such a way that space gets expanded around the high probability region of function optimum and shrinks around low probability region of optimum. We incorporate this prior directly in function model (Gaussian process), by redefining the kernel matrix, which allows this method to work with any acquisition function, i.e. acquisition agnostic approach. We show the superiority of our method over standard Bayesian optimisation method through optimisation of several benchmark functions and hyperparameter tuning of two algorithms: Support Vector Machine (SVM) and Random forest.

History

Journal

Knowledge-Based Systems

Volume

195

Article number

ARTN 105663

Pagination

1 - 11

Location

Amsterdam, The Netherlands

Open access

  • Yes

ISSN

0950-7051

eISSN

1872-7409

Language

English

Publication classification

C1 Refereed article in a scholarly journal

Publisher

ELSEVIER