Active Sequential Posterior Estimation for Sample-Efficient Simulation-Based Inference
This addresses the problem of resource-intensive inference for researchers and practitioners using simulation-based models, particularly in high-dimensional domains like traffic simulation, though it is incremental as it builds on existing posterior estimation methods.
The paper tackles the challenge of performing inference under simulation models, which often requires many simulation samples and struggles with high-dimensional settings, by introducing active sequential neural posterior estimation (ASNPE) that integrates active learning to improve sample efficiency. The method outperforms benchmarks and state-of-the-art methods on a real-world traffic network and SBI benchmarks, demonstrating concrete performance advantages.
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.