Calibrating Agent-Based Financial Markets Simulators with Pretrainable Automatic Posterior Transformation-Based Surrogates

2026-01-11

arXiv.org

AI Summary

This work addresses the challenges in calibrating agent-based models (ABMs) in finance, where high simulation costs, multimodal and nonlinear objective landscapes, and the lack of cross-task knowledge transfer hinder existing surrogate-assisted approaches. To overcome these limitations, the authors propose ANTR, a novel calibration framework that introduces, for the first time, a pretrainable neural density estimator to directly model the posterior distribution of model parameters. ANTR integrates automatic posterior transformation, negative-correlation diversity search, and an adaptive trust-region mechanism to achieve efficient and accurate calibration. The method supports knowledge transfer across tasks and demonstrates superior performance over conventional metaheuristics and state-of-the-art surrogate-assisted evolutionary algorithms under diverse market conditions, particularly excelling in batch calibration scenarios by significantly improving both accuracy and computational efficiency.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Search and Optimization: Metareasoning and Metaheuristics
• Multiagent Systems: Mechanism Design

Application Category

• Search and Retrieval-Augmented AI: Agentic search
• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Calibrating Agent-Based Models (ABMs) is an important optimization problem for simulating the complex social systems, where the goal is to identify the optimal parameter of a given ABM by minimizing the discrepancy between the simulated data and the real-world observations. Unfortunately, it suffers from the extensive computational costs of iterative evaluations, which involves the expensive simulation with the candidate parameter. While Surrogate-Assisted Evolutionary Algorithms (SAEAs) have been widely adopted to alleviate the computational burden, existing methods face two key limitations: 1) surrogating the original evaluation function is hard due the nonlinear yet multi-modal nature of the ABMs, and 2) the commonly used surrogates cannot share the optimization experience among multiple calibration tasks, making the batched calibration less effective. To address these issues, this work proposes Automatic posterior transformation with Negatively Correlated Search and Adaptive Trust-Region (ANTR). ANTR first replaces the traditional surrogates with a pretrainable neural density estimator that directly models the posterior distribution of the parameters given observed data, thereby aligning the optimization objective with parameter-space accuracy. Furthermore, we incorporate a diversity-preserving search strategy to prevent premature convergence and an adaptive trust-region method to efficiently allocate computational resources. We take two representative ABM-based financial market simulators as the test bench as due to the high non-linearity. Experiments demonstrate that the proposed ANTR significantly outperforms conventional metaheuristics and state-of-the-art SAEAs in both calibration accuracy and computational efficiency, particularly in batch calibration scenarios across multiple market conditions.

Problem

• Agent-Based Models
• Calibration
• Surrogate-Assisted Optimization
• Financial Market Simulation
• Computational Efficiency

Innovation

• Surrogate-Assisted Evolutionary Algorithms
• Neural Density Estimation
• Posterior Modeling
• Batch Calibration
• Agent-Based Modeling