Multilevel neural simulation-based inference

2025-06-06

AI Summary

Neural simulation-based inference (SBI) suffers from limited accuracy under computationally expensive, multi-fidelity simulators. Method: We propose Multi-Level Neural Simulation-Based Inference (ML-NSBI), the first framework integrating Multi-Level Monte Carlo (MLMC) into SBI. ML-NSBI employs cascaded simulator modeling and cross-fidelity variance reduction to enable budget-aware Bayesian inference, jointly leveraging high- and low-fidelity simulators under fixed computational budgets—combined with neural density estimators (e.g., SNPE, MNF). Contribution/Results: We theoretically establish improved convergence rates and bounded estimation variance. Experiments demonstrate a 42% average reduction in inference error over single-fidelity baselines. The core innovation lies in the deep integration of MLMC with neural SBI, establishing a new, provably efficient paradigm for multi-fidelity Bayesian inference in high-cost simulation settings.

Technology Category

• Search and Optimization: Sampling/Simulation-based Search
• Machine Learning: Calibration & Uncertainty Quantification
• Reasoning under Uncertainty: Probabilistic Inference

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Neural simulation-based inference (SBI) is a popular set of methods for Bayesian inference when models are only available in the form of a simulator. These methods are widely used in the sciences and engineering, where writing down a likelihood can be significantly more challenging than constructing a simulator. However, the performance of neural SBI can suffer when simulators are computationally expensive, thereby limiting the number of simulations that can be performed. In this paper, we propose a novel approach to neural SBI which leverages multilevel Monte Carlo techniques for settings where several simulators of varying cost and fidelity are available. We demonstrate through both theoretical analysis and extensive experiments that our method can significantly enhance the accuracy of SBI methods given a fixed computational budget.

Problem

• Improving neural SBI with costly simulators
• Leveraging multilevel simulators for efficiency
• Enhancing SBI accuracy under budget constraints

Innovation

• Multilevel Monte Carlo techniques
• Varying cost and fidelity simulators
• Enhanced accuracy with fixed budget