MISO-wiLDCosts: Multi Information Source Optimization with Location Dependent Costs

TL;DR

This paper introduces a novel multi-source optimization method that models location-dependent costs and fidelities using Gaussian Processes, improving decision-making in black-box optimization tasks.

Contribution

It proposes an augmented Gaussian Process framework combined with a cost model to optimize source selection considering variable costs and fidelities across locations.

Findings

Effective in hyperparameter optimization tasks

Reduces query costs by considering location-dependent costs

Improves optimization efficiency over traditional methods

Abstract

This paper addresses black-box optimization over multiple information sources whose both fidelity and query cost change over the search space, that is they are location dependent. The approach uses: (i) an Augmented Gaussian Process, recently proposed in multi-information source optimization as a single model of the objective function over search space and sources, and (ii) a Gaussian Process to model the location-dependent cost of each source. The former is used into a Confidence Bound based acquisition function to select the next source and location to query, while the latter is used to penalize the value of the acquisition depending on the expected query cost for any source-location pair. The proposed approach is evaluated on a set of Hyperparameters Optimization tasks, consisting of two Machine Learning classifiers and three datasets of different sizes.