Reproduce “Energy-aware frugal Bayesian optimization” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Gaston Plat, Paul Saves, Nathalie Bartoli, Thierry Lefebvre, Joseph Morlier
The authors use Bayesian optimization to search model settings balancing measured energy and optimization performance. In a 10-bar truss example, the Pareto-optimal probability-of-improvement setting used 594.9 ± 222.8 Wh and found a 1742 ± 10.5 kg feasible mass minimum, versus 6459 ± 2279 Wh and 2858 ± 500.0 kg for an empirical baseline; the searches may not have fully converged.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.