1 code implementation • 15 Jun 2022 • Alma Rahat, Tinkle Chugh, Jonathan Fieldsend, Richard Allmendinger, Kaisa Miettinen
Using the predictive densities, we can compute the expected hypervolume improvement (EHVI) due to a solution.
no code implementations • 2 May 2022 • Tinkle Chugh
In this work, we overcome these limitations by building a surrogate model for each objective function and show that the scalarising function distribution is not Gaussian.
no code implementations • 27 Apr 2022 • Tinkle Chugh
In many real-world problems, a decision-maker has some preferences on the objective functions.
1 code implementation • 31 Mar 2022 • George De Ath, Tinkle Chugh, Alma A. M. Rahat
In this work we present MBORE: multi-objective Bayesian optimisation by density-ratio estimation, and compare it to BO across a range of synthetic and real-world benchmarks.
no code implementations • 31 Mar 2022 • Tinkle Chugh, Endi Ymeraj
Wind energy is one of the cleanest renewable electricity sources and can help in addressing the challenge of climate change.
no code implementations • 10 Apr 2021 • Clym Stock-Williams, Tinkle Chugh, Alma Rahat, Wei Yu
Performing multi-objective Bayesian optimisation by scalarising the objectives avoids the computation of expensive multi-dimensional integral-based acquisition functions, instead of allowing one-dimensional standard acquisition functions\textemdash such as Expected Improvement\textemdash to be applied.
no code implementations • 11 Apr 2019 • Tinkle Chugh
However, their use in solving (computationally) expensive multi- and many-objective optimization problems in Bayesian multiobjective optimization is scarce.