Bayesian optimization with Gaussian processes: Insights from hyperspectral trait search

Azam, Ruhana

Permalink

https://hdl.handle.net/2142/122148 Copy

Description

Title

Bayesian optimization with Gaussian processes: Insights from hyperspectral trait search

Author(s)

Azam, Ruhana

Issue Date

2023-12-04

Director of Research (if dissertation) or Advisor (if thesis)

Koyejo, Sanmi

Department of Study

Computer Science

Discipline

Computer Science

Degree Granting Institution

University of Illinois at Urbana-Champaign

Degree Name

M.S.

Degree Level

Thesis

Keyword(s)

• Bayesian Optimization
• Gaussian Process
• Genomic prediction

Abstract

The application of Bayesian Optimization using Gaussian Processes (BO-GP) for global optimization problems is ubiquitous across scientific disciplines because, beyond good performance, it supports exact inference, is interpretable, and has straightforward uncertainty quantification. In this thesis, we reexamine the biological application of BO-GP in searching trait spaces for genomic prediction, which uses genome-wide marker information to predict breeding values for agronomically important traits. Genomic predictions help breeders select desirable plants earlier in the field season without waiting to observe traits later. To reduce costs of collecting data for genomic prediction models, low-cost, hyperspectral data, which are highly correlated with desired traits, can be utilized as a proxy. While these hyperspectral spaces are known to be sharp and aperiodic, BO-GP is considered a feasible approach. However, our work finds that a simple random search surprisingly achieves comparable performance to BO-GP while requiring significantly less computing cost. Through a careful investigation, we can explain this observation as a limitation of the standard implementation and use of BO-GP (e.g., the default use of Matérn kernels), for sharp and aperiodic functions -- where the incompatible structure results in samples similar to random search but with higher computational cost.

Graduation Semester

2023-12

Type of Resource

Thesis

Handle URL

https://hdl.handle.net/2142/122148

Copyright and License Information

Copyright 2023 Ruhana Azam

Owning Collections