Energy-aware frugal Bayesian optimization
Abstract
Modern design optimization frameworks aim first and foremost for models with the most accurate predictions without balancing computational overhead. It remains a reason why scaled architecture and multidisciplinary design optimization problems are difficult to address, even with sample-efficient Bayesian optimizers. In this paper, a metric quantifying the computational energy footprint is introduced within a Bayesian optimization framework to guide the parameter setting of a model towards configurations that balance both performance and frugality. The computer experiments highlighted existing tradeoffs between optimum convergence and the underlying energy footprint, and sometimes resulted in both a better-found optimum and lower energy consumption.
Versions
Related
- Learning What to Evaluate: Correlation-Aware Decoupling for Multiobjective Bayesian Optimization
- Cost-Aware Stopping for Freeze-Thaw Bayesian Optimization: When Does One-Step Lookahead Suffice?
- UQ-ACE: Stability-Aware Counterfactual Controller Tuning via Bayesian SINDy
- Transfer learning in bayesian optimization for aircraft design
- Efficient Cost-Aware LLM Evaluation via Bayesian Bandit Gittins Indices
BibTeX
@misc{plat2026energyaware,
title = {{Energy-aware frugal Bayesian optimization}},
author = {Gaston Plat and Paul Saves and Nathalie Bartoli and Thierry Lefebvre and Joseph Morlier},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.31638},
eprint = {2609.31638},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.31638},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Energy-aware frugal Bayesian optimization
AU - Gaston Plat
AU - Paul Saves
AU - Nathalie Bartoli
AU - Thierry Lefebvre
AU - Joseph Morlier
PY - 2026
DA - 2026/09/11
PB - arXiv
DO - 10.48550/arxiv.2609.31638
UR - https://arxiv.org/abs/2609.31638
AB - Modern design optimization frameworks aim first and foremost for models with the most accurate predictions without balancing computational overhead. It remains a reason why scaled architecture and multidisciplinary design optimization problems are difficult to address, even with sample-efficient Bayesian optimizers. In this paper, a metric quantifying the computational energy footprint is introduced within a Bayesian optimization framework to guide the parameter setting of a model towards configurations that balance both performance and frugality. The computer experiments highlighted existing tradeoffs between optimum convergence and the underlying energy footprint, and sometimes resulted in both a better-found optimum and lower energy consumption.
ER -