Պահպանված է:
Մատենագիտական մանրամասներ
Հիմնական հեղինակներ: Ahmadianshalchi, Alaleh, Belakaria, Syrine, Doppa, Janardhan Rao
Ձևաչափ: Preprint
Հրապարակվել է: 2024
Խորագրեր:
Առցանց հասանելիություն:https://arxiv.org/abs/2406.08799
Ցուցիչներ: Ավելացրեք ցուցիչ
Չկան պիտակներ, Եղեք առաջինը, ով նշում է այս գրառումը!
_version_ 1866916285279895552
author Ahmadianshalchi, Alaleh
Belakaria, Syrine
Doppa, Janardhan Rao
author_facet Ahmadianshalchi, Alaleh
Belakaria, Syrine
Doppa, Janardhan Rao
contents We consider the problem of multi-objective optimization (MOO) of expensive black-box functions with the goal of discovering high-quality and diverse Pareto fronts where we are allowed to evaluate a batch of inputs. This problem arises in many real-world applications including penicillin production where diversity of solutions is critical. We solve this problem in the framework of Bayesian optimization (BO) and propose a novel approach referred to as Pareto front-Diverse Batch Multi-Objective BO (PDBO). PDBO tackles two important challenges: 1) How to automatically select the best acquisition function in each BO iteration, and 2) How to select a diverse batch of inputs by considering multiple objectives. We propose principled solutions to address these two challenges. First, PDBO employs a multi-armed bandit approach to select one acquisition function from a given library. We solve a cheap MOO problem by assigning the selected acquisition function for each expensive objective function to obtain a candidate set of inputs for evaluation. Second, it utilizes Determinantal Point Processes (DPPs) to choose a Pareto-front-diverse batch of inputs for evaluation from the candidate set obtained from the first step. The key parameters for the methods behind these two steps are updated after each round of function evaluations. Experiments on multiple MOO benchmarks demonstrate that PDBO outperforms prior methods in terms of both the quality and diversity of Pareto solutions.
format Preprint
id arxiv_https___arxiv_org_abs_2406_08799
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Pareto Front-Diverse Batch Multi-Objective Bayesian Optimization
Ahmadianshalchi, Alaleh
Belakaria, Syrine
Doppa, Janardhan Rao
Machine Learning
Artificial Intelligence
We consider the problem of multi-objective optimization (MOO) of expensive black-box functions with the goal of discovering high-quality and diverse Pareto fronts where we are allowed to evaluate a batch of inputs. This problem arises in many real-world applications including penicillin production where diversity of solutions is critical. We solve this problem in the framework of Bayesian optimization (BO) and propose a novel approach referred to as Pareto front-Diverse Batch Multi-Objective BO (PDBO). PDBO tackles two important challenges: 1) How to automatically select the best acquisition function in each BO iteration, and 2) How to select a diverse batch of inputs by considering multiple objectives. We propose principled solutions to address these two challenges. First, PDBO employs a multi-armed bandit approach to select one acquisition function from a given library. We solve a cheap MOO problem by assigning the selected acquisition function for each expensive objective function to obtain a candidate set of inputs for evaluation. Second, it utilizes Determinantal Point Processes (DPPs) to choose a Pareto-front-diverse batch of inputs for evaluation from the candidate set obtained from the first step. The key parameters for the methods behind these two steps are updated after each round of function evaluations. Experiments on multiple MOO benchmarks demonstrate that PDBO outperforms prior methods in terms of both the quality and diversity of Pareto solutions.
title Pareto Front-Diverse Batch Multi-Objective Bayesian Optimization
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2406.08799