Joel Dyer, Patrick Cannon, J. Doyne Farmer, Sebastian Schmon
arXiv 1 Feb 2022 · Econometrics · publishedJournal of Economic Dynamics and Control (2024) · 28 citations (OpenAlex)
arXiv:2202.00625 · PDF · DOI · OpenAlex · Extracted main text
Simulation models, in particular agent-based models, are gaining popularity in economics. The considerable flexibility they offer, as well as their capacity to reproduce a variety of empirically observed behaviours of complex systems, give them broad appeal, and the increasing availability of cheap computing power has made their use feasible. Yet a widespread adoption in real-world modelling and decision-making scenarios has been hindered by the difficulty of performing parameter estimation for such models. In general, simulation models lack a tractable likelihood function, which precludes a straightforward application of standard statistical inference techniques. Several recent works have sought to address this problem through the application of likelihood-free inference techniques, in which parameter estimates are determined by performing some form of comparison between the observed data and simulation output. However, these approaches are (a) founded on restrictive assumptions, and/or (b) typically require many hundreds of thousands of simulations. These qualities make them unsuitable for large-scale simulations in economics and can cast doubt on the validity of these inference methods in such scenarios. In this paper, we investigate the efficacy of two classes of black-box approximate Bayesian inference methods that have recently drawn significant attention within the probabilistic machine learning community: neural posterior estimation and neural density ratio estimation. We present benchmarking experiments in which we demonstrate that neural network based black-box methods provide state of the art parameter inference for economic simulation models, and crucially are compatible with generic multivariate time-series data. In addition, we suggest appropriate assessment criteria for future benchmarking of approximate Bayesian inference procedures for economic simulation models.
appendix boundary found by appendix_command · 96% of the source is main text. Read the extracted text to check this.
The works this paper leans on most, across its whole bibliography — not restricted to papers in our corpus. Ranked by composite intensity, which combines how often a work is mentioned, how many sections mention it, and how much of that falls in the main text rather than the appendix.
| Reference | Intensity | Mentions | Sections | Main text | |
|---|---|---|---|---|---|
| 1 | Jakob Grazzini, Matteo G Richiardi, and Mike Tsionas (2017) Bayesian estimation of agent-based models | 1.000 | 18 | 5 | 100% |
| 2 | Donovan Platt (2021) Bayesian estimation of economic simulation models using neural networks | 1.000 | 9 | 6 | 100% |
| 3 | Donovan Platt (2020) A comparison of economic agent-based model calibration methods | 1.000 | 5 | 3 | 100% |
| 4 | David S. Greenberg, Marcel Nonnenmacher, and Jakob H. Macke (2019) Automatic posterior transformation for likelihood-free inference | 0.874 | 6 | 2 | 100% |
| 5 | Conor Durkan, Iain Murray, and George Papamakarios (2020) On Contrastive Learning for Likelihood-free Inference | 0.874 | 5 | 2 | 100% |
| 6 | George Papamakarios and Iain Murray (2016) Fast $$-free inference of simulation models with bayesian conditional density estimation | 0.811 | 4 | 2 | 100% |
| 7 | Joeri Hermans, Volodimir Begy, and Gilles Louppe (2020) Likelihood-free MCMC with amortized approximate ratio estimators | 0.811 | 4 | 2 | 100% |
| 8 | Takashi Shiono (2021) Estimation of agent-based models using bayesian deep learning approach of bayesflow | 0.811 | 4 | 2 | 100% |
| 9 | Jan-Matthis Lueckmann, Pedro J Goncalves, Giacomo Bassetto, Kaan Öca… (2017) Flexible statistical inference for mechanistic models of neural dynamics | 0.737 | 3 | 2 | 100% |
| 10 | Thomas Lux (2021) Bayesian estimation of agent-based models via adaptive particle markov chain monte carlo | 0.737 | 3 | 2 | 100% |
Showing the top 10 of 79 scored citations.
arXiv econ.EM papers that cite this one, ranked by how heavily they lean on it.
| Citing paper | Intensity | Mentions | Sections | |
|---|---|---|---|---|
| 1 | Amortized Neural Networks for Agent-Based Model Forecasting | 0.405 | 1 | 1 |