icdm_main.pdf (997.85 kB)
Accelerating experimental design by incorporating experimenter hunches
Version 3 2023-10-04, 02:07
Version 2 2023-10-02, 22:42
Version 1 2019-03-01, 11:38
conference contribution
posted on 2023-10-04, 02:07 authored by C Li, R Santu, S Gupta, V Nguyen, S Venkatesh, A Sutti, DR De Celis Leal, T Slezak, M Height, M Mohammed, I GibsonExperimental design is a process of obtaining a product with target property via experimentation. Bayesian optimization offers a sample-efficient tool for experimental design when experiments are expensive. Often, expert experimenters have 'hunches' about the behavior of the experimental system, offering potentials to further improve the efficiency. In this paper, we consider per-variable monotonic trend in the underlying property that results in a unimodal trend in those variables for a target value optimization. For example, sweetness of a candy is monotonic to the sugar content. However, to obtain a target sweetness, the utility of the sugar content becomes a unimodal function, which peaks at the value giving the target sweetness and falls off both ways. In this paper, we propose a novel method to solve such problems that achieves two main objectives: a) the monotonicity information is used to the fullest extent possible, whilst ensuring that b) the convergence guarantee remains intact. This is achieved by a two-stage Gaussian process modeling, where the first stage uses the monotonicity trend to model the underlying property, and the second stage uses 'virtual' samples, sampled from the first, to model the target value optimization function. The process is made theoretically consistent by adding appropriate adjustment factor in the posterior computation, necessitated because of using the 'virtual' samples. The proposed method is evaluated through both simulations and real world experimental design problems of a) new short polymer fiber with the target length, and b) designing of a new three dimensional porous scaffolding with a target porosity. In all scenarios our method demonstrates faster convergence than the basic Bayesian optimization approach not using such 'hunches'.
History
Volume
2018-NovemberPagination
257-266Location
SingaporePublisher DOI
Open access
- Yes
Start date
2018-11-17End date
2018-11-20ISSN
1550-4786ISBN-13
9781538691588Language
engPublication classification
E Conference publication, E1 Full written paper - refereedTitle of proceedings
IEEE ICDM 2018 : International Conference on Data MiningEvent
Data Mining. International Conference (2018 : Singapore)Publisher
IEEEPlace of publication
Piscataway, N.J.Usage metrics
Categories
Keywords
bayesian optimizationmonotonicity knowledgeprior knowledgehyper-parameter tuningexperimental designSchool of Information TechnologyInstitute for Frontier MaterialsPattern Recognition and Data AnalyticsARC Laureate FL1701000064609 Information systemsInformation SystemsArtificial Intelligence and Image ProcessingDistributed Computing
Licence
Exports
RefWorks
BibTeX
Ref. manager
Endnote
DataCite
NLM
DC