Papers for

software performance engineers

Papers whose findings have a practical use for this group, as judged from the abstract. Open a paper to read what it means in practice.

Bayesian optimisation improves speed using local Gaussian process experts

Bayesian Optimisation Using Product-of-Experts Gaussian Process Models with Uncertainty Calibration

Abstract: Bayesian optimisation (BO) typically relies on a single global Gaussian process (GP) model as its surrogate model. However, GP regression has cubic computational complexity in the number of training data points, limiting its applicability to large-scale optimisation problems. The product-of-experts Gaussian process model with uncertainty calibration (GP-pro-c) mitigates this limitation by combining multiple local GP experts, enabling improved uncertainty quantification, reduced computational cost, and preservation of global correlations. Despite these desirable properties, the use of GP-pro-c in BO has not been thoroughly studied. This paper introduces BO-pro-c, a Bayesian optimisation algorithm that uses GP-pro-c as its surrogate model, and evaluate its performance across a diverse range of BO settings. Experimental results suggest that BO-pro-c maintains competitive optimisation performance while achieving a 0.9% reduction in simple regret and a 39.4% reduction in computational overhead relative to a BO algorithm based on a single global GP model.

Mon 14 SeptMachine Learning
The gist
Bayesian optimisation is a method to find the best solution to a problem by trying different options and learning from them. Normally, it uses one big model that becomes slow when there’s a lot of data. The authors propose using many smaller models that each look at part of the data and work together to make decisions. This approach keeps good accuracy while running faster, making it better for big problems.
Open 2609.15555v1