Human-in-the-Loop Meta Bayesian Optimization for Fusion Energy and Scientific Applications
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911637507670016 |
|---|---|
| author | Gutierrez, Ricardo Luna Ghorbanpour, Sahand Rahman, Ejaz Gopalaswamy, Varchas Betti, Riccardo Gundecha, Vineet Lees, Aarne Sarkar, Soumyendu |
| author_facet | Gutierrez, Ricardo Luna Ghorbanpour, Sahand Rahman, Ejaz Gopalaswamy, Varchas Betti, Riccardo Gundecha, Vineet Lees, Aarne Sarkar, Soumyendu |
| contents | Inertial Confinement Fusion (ICF) holds transformative promise for sustainable, near-limitless clean energy, yet remains constrained by prohibitively high costs and limited experimental opportunities. This paper presents Human-in-the-Loop Meta Bayesian Optimization (HL-MBO), a framework that integrates expert knowledge with few-shot, uncertainty-aware machine learning to accelerate discovery in data-scarce, high-stakes scientific domains. HL-MBO introduces a meta-learned surrogate model with an expert-informed acquisition function to recommend candidate experiments. To foster trust and enable informed decisions, HL-MBO also provides interpretable explanations of its suggestions. We show HL-MBO outperforms current BO methods on ICF energy yield optimization, as well as benchmarks in molecular optimization and critical temperature maximization for superconducting materials. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_00068 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Human-in-the-Loop Meta Bayesian Optimization for Fusion Energy and Scientific Applications Gutierrez, Ricardo Luna Ghorbanpour, Sahand Rahman, Ejaz Gopalaswamy, Varchas Betti, Riccardo Gundecha, Vineet Lees, Aarne Sarkar, Soumyendu Machine Learning Artificial Intelligence Plasma Physics Inertial Confinement Fusion (ICF) holds transformative promise for sustainable, near-limitless clean energy, yet remains constrained by prohibitively high costs and limited experimental opportunities. This paper presents Human-in-the-Loop Meta Bayesian Optimization (HL-MBO), a framework that integrates expert knowledge with few-shot, uncertainty-aware machine learning to accelerate discovery in data-scarce, high-stakes scientific domains. HL-MBO introduces a meta-learned surrogate model with an expert-informed acquisition function to recommend candidate experiments. To foster trust and enable informed decisions, HL-MBO also provides interpretable explanations of its suggestions. We show HL-MBO outperforms current BO methods on ICF energy yield optimization, as well as benchmarks in molecular optimization and critical temperature maximization for superconducting materials. |
| title | Human-in-the-Loop Meta Bayesian Optimization for Fusion Energy and Scientific Applications |
| topic | Machine Learning Artificial Intelligence Plasma Physics |
| url | https://arxiv.org/abs/2605.00068 |