Active Sequential Posterior Estimation for Sample-Efficient Simulation-Based Inference

TL;DR

This paper introduces ASNPE, an active learning approach for simulation-based inference that improves sample efficiency and scalability in high-dimensional inverse problems, demonstrated on traffic simulation and benchmark environments.

Contribution

ASNPE integrates active learning into neural posterior estimation, significantly reducing simulation samples needed for accurate inference in complex models.

Findings

Outperforms existing methods on real-world traffic network data

Achieves better sample efficiency in high-dimensional SBI tasks

Demonstrates scalability and effectiveness across multiple benchmarks

Abstract

Computer simulations have long presented the exciting possibility of scientific insight into complex real-world processes. Despite the power of modern computing, however, it remains challenging to systematically perform inference under simulation models. This has led to the rise of simulation-based inference (SBI), a class of machine learning-enabled techniques for approaching inverse problems with stochastic simulators. Many such methods, however, require large numbers of simulation samples and face difficulty scaling to high-dimensional settings, often making inference prohibitive under resource-intensive simulators. To mitigate these drawbacks, we introduce active sequential neural posterior estimation (ASNPE). ASNPE brings an active learning scheme into the inference loop to estimate the utility of simulation parameter candidates to the underlying probabilistic model. The proposed acquisition scheme is easily integrated into existing posterior estimation pipelines, allowing for improved sample efficiency with low computational overhead. We further demonstrate the effectiveness of the proposed method in the travel demand calibration setting, a high-dimensional inverse problem commonly requiring computationally expensive traffic simulators. Our method outperforms well-tuned benchmarks and state-of-the-art posterior estimation methods on a large-scale real-world traffic network, as well as demonstrates a performance advantage over non-active counterparts on a suite of SBI benchmark environments.