Asynchronous, Generation-Free ABC: Streaming AMIS Reweighting for Heterogeneous Simulator Workloads on HPC
Abstract
Approximate Bayesian computation (ABC) enables Bayesian inference for models with intractable likelihoods by estimating parameter posterior distributions from simulated data. Sequential ABC methods improve sampling efficiency by iteratively adapting the proposal distribution toward regions of high posterior probability. However, these methods typically operate in generations, where each generation must wait for its slowest simulation before the next can begin. On a parallel machine, this synchronization barrier leaves workers idle and reduces throughput, particularly when simulation runtimes vary substantially. We introduce a generation-free ABC sampler that updates its proposal when simulation results arrive and sends a new candidate to each available worker. The proposal is based on the best particles evaluated so far. To estimate the posterior, we reuse the full history and reweight particles against a reconstructed mixture of sampling proposals. We show how errors in approximating the mixture of sampling proposals affect the estimated posterior and establish consistency for the smooth-ABC posterior when the approximation becomes asymptotically exact. In our experiments, the method achieves well-calibrated posterior estimates where a pyABC baseline with the same kernel and bandwidth schedule under-covers. From the asynchronous run's timing alone, we predict how much a synchronization barrier would slow the sampler. These predictions agree with measured synchronization penalties ranging from 1.2x to 400x. On a Cellular Potts tissue simulator, the asynchronous sampler completes 2.1-2.4x as many evaluations as pyABC in the same hour, and the discrepancy threshold for its best 100 evaluations is 4.1x smaller. With the starting bandwidth set from prior-predictive discrepancies, it also produces a more concentrated two-parameter posterior with a larger effective sample size than pyABC.
Related
- Bridging the Gap Between Homogeneous and Heterogeneous Asynchronous Optimization Is Surprisingly Difficult
- Renewable Online Expectile Regression for Heterogeneous Streaming Data with Abnormal Batches
- Fast Calibration of Generalized Posteriors via Dirichlet Reweighting
- Q-MMR: Off-Policy Evaluation via Recursive Reweighting and Moment Matching
- Stability of Change-of-Numéraire Reweighting: An Exact Wasserstein Boundary
BibTeX
@misc{herold2026asynchronous,
title = {{Asynchronous, Generation-Free ABC: Streaming AMIS Reweighting for Heterogeneous Simulator Workloads on HPC}},
author = {Julian Herold and Markus Götz and Alexander Schug},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.29506},
eprint = {2610.29506},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.29506},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Asynchronous, Generation-Free ABC: Streaming AMIS Reweighting for Heterogeneous Simulator Workloads on HPC
AU - Julian Herold
AU - Markus Götz
AU - Alexander Schug
PY - 2026
DA - 2026/10/21
PB - arXiv
DO - 10.48550/arxiv.2610.29506
UR - https://arxiv.org/abs/2610.29506
AB - Approximate Bayesian computation (ABC) enables Bayesian inference for models with intractable likelihoods by estimating parameter posterior distributions from simulated data. Sequential ABC methods improve sampling efficiency by iteratively adapting the proposal distribution toward regions of high posterior probability. However, these methods typically operate in generations, where each generation must wait for its slowest simulation before the next can begin. On a parallel machine, this synchronization barrier leaves workers idle and reduces throughput, particularly when simulation runtimes vary substantially. We introduce a generation-free ABC sampler that updates its proposal when simulation results arrive and sends a new candidate to each available worker. The proposal is based on the best particles evaluated so far. To estimate the posterior, we reuse the full history and reweight particles against a reconstructed mixture of sampling proposals. We show how errors in approximating the mixture of sampling proposals affect the estimated posterior and establish consistency for the smooth-ABC posterior when the approximation becomes asymptotically exact. In our experiments, the method achieves well-calibrated posterior estimates where a pyABC baseline with the same kernel and bandwidth schedule under-covers. From the asynchronous run's timing alone, we predict how much a synchronization barrier would slow the sampler. These predictions agree with measured synchronization penalties ranging from 1.2x to 400x. On a Cellular Potts tissue simulator, the asynchronous sampler completes 2.1-2.4x as many evaluations as pyABC in the same hour, and the discrepancy threshold for its best 100 evaluations is 4.1x smaller. With the starting bandwidth set from prior-predictive discrepancies, it also produces a more concentrated two-parameter posterior with a larger effective sample size than pyABC.
ER -