Research

Paper

TESTING March 16, 2026

Scalable Simulation-Based Model Inference with Test-Time Complexity Control

Authors

Manuel Gloeckler, J. P. Manzano-Patrón, Stamatios N. Sotiropoulos, Cornelius Schröder, Jakob H. Macke

Abstract

Simulation plays a central role in scientific discovery. In many applications, the bottleneck is no longer running a simulator; it is choosing among large families of plausible simulators, each corresponding to different forward models/hypotheses consistent with observations. Over large model families, classical Bayesian workflows for model selection are impractical. Furthermore, amortized model selection methods typically hard-code a fixed model prior or complexity penalty at training time, requiring users to commit to a particular parsimony assumption before seeing the data. We introduce PRISM, a simulation-based encoder-decoder that infers a joint posterior over both discrete model structures and associated continuous parameters, while enabling test-time control of model complexity via a tunable model prior that the network is conditioned on. We show that PRISM scales to families with combinatorially many (up to billions) of model instantiations on a synthetic symbolic regression task. As a scientific application, we evaluate PRISM on biophysical modeling for diffusion MRI data, showing the ability to perform model selection across several multi-compartment models, on both synthetic and in vivo neuroimaging data.

Metadata

arXiv ID: 2603.15292
Provider: ARXIV
Primary Category: stat.ML
Published: 2026-03-16
Fetched: 2026-03-17 06:02

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.15292v1</id>\n    <title>Scalable Simulation-Based Model Inference with Test-Time Complexity Control</title>\n    <updated>2026-03-16T13:54:15Z</updated>\n    <link href='https://arxiv.org/abs/2603.15292v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.15292v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>Simulation plays a central role in scientific discovery. In many applications, the bottleneck is no longer running a simulator; it is choosing among large families of plausible simulators, each corresponding to different forward models/hypotheses consistent with observations. Over large model families, classical Bayesian workflows for model selection are impractical. Furthermore, amortized model selection methods typically hard-code a fixed model prior or complexity penalty at training time, requiring users to commit to a particular parsimony assumption before seeing the data. We introduce PRISM, a simulation-based encoder-decoder that infers a joint posterior over both discrete model structures and associated continuous parameters, while enabling test-time control of model complexity via a tunable model prior that the network is conditioned on. We show that PRISM scales to families with combinatorially many (up to billions) of model instantiations on a synthetic symbolic regression task. As a scientific application, we evaluate PRISM on biophysical modeling for diffusion MRI data, showing the ability to perform model selection across several multi-compartment models, on both synthetic and in vivo neuroimaging data.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='stat.ML'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.AI'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.LG'/>\n    <published>2026-03-16T13:54:15Z</published>\n    <arxiv:primary_category term='stat.ML'/>\n    <author>\n      <name>Manuel Gloeckler</name>\n    </author>\n    <author>\n      <name>J. P. Manzano-Patrón</name>\n    </author>\n    <author>\n      <name>Stamatios N. Sotiropoulos</name>\n    </author>\n    <author>\n      <name>Cornelius Schröder</name>\n    </author>\n    <author>\n      <name>Jakob H. Macke</name>\n    </author>\n  </entry>"
}