Supercharging Simulation-Based Inference for Bayesian Optimal Experimental Design
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866908818121687040 |
|---|---|
| author | Klein, Samuel Neiswanger, Willie Ratner, Daniel Kagan, Michael Gasiorowski, Sean |
| author_facet | Klein, Samuel Neiswanger, Willie Ratner, Daniel Kagan, Michael Gasiorowski, Sean |
| contents | Bayesian optimal experimental design (BOED) seeks to maximize the expected information gain (EIG) of experiments. This requires a likelihood estimate, which in many settings is intractable. Simulation-based inference (SBI) provides powerful tools for this regime. However, existing work explicitly connecting SBI and BOED is restricted to a single contrastive EIG bound. We show that the EIG admits multiple formulations which can directly leverage modern SBI density estimators, encompassing neural posterior, likelihood, and ratio estimation. Building on this perspective, we define a novel EIG estimator using neural likelihood estimation. Further, we identify optimization as a key bottleneck of gradient based EIG maximization and show that a simple multi-start parallel gradient ascent procedure can substantially improve reliability and performance. With these innovations, our SBI-based BOED methods are able to match or outperform by up to $22\%$ existing state-of-the-art approaches across standard BOED benchmarks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_06900 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Supercharging Simulation-Based Inference for Bayesian Optimal Experimental Design Klein, Samuel Neiswanger, Willie Ratner, Daniel Kagan, Michael Gasiorowski, Sean Machine Learning Artificial Intelligence Information Theory Neural and Evolutionary Computing Bayesian optimal experimental design (BOED) seeks to maximize the expected information gain (EIG) of experiments. This requires a likelihood estimate, which in many settings is intractable. Simulation-based inference (SBI) provides powerful tools for this regime. However, existing work explicitly connecting SBI and BOED is restricted to a single contrastive EIG bound. We show that the EIG admits multiple formulations which can directly leverage modern SBI density estimators, encompassing neural posterior, likelihood, and ratio estimation. Building on this perspective, we define a novel EIG estimator using neural likelihood estimation. Further, we identify optimization as a key bottleneck of gradient based EIG maximization and show that a simple multi-start parallel gradient ascent procedure can substantially improve reliability and performance. With these innovations, our SBI-based BOED methods are able to match or outperform by up to $22\%$ existing state-of-the-art approaches across standard BOED benchmarks. |
| title | Supercharging Simulation-Based Inference for Bayesian Optimal Experimental Design |
| topic | Machine Learning Artificial Intelligence Information Theory Neural and Evolutionary Computing |
| url | https://arxiv.org/abs/2602.06900 |