Generalized Bayesian Inference for Scientific Simulators via Amortized
Cost Estimation
- URL: http://arxiv.org/abs/2305.15208v2
- Date: Thu, 2 Nov 2023 10:08:16 GMT
- Title: Generalized Bayesian Inference for Scientific Simulators via Amortized
Cost Estimation
- Authors: Richard Gao, Michael Deistler, Jakob H. Macke
- Abstract summary: We train a neural network to approximate the cost function, which we define as the expected distance between simulations produced by a parameter and observed data.
We show that, on several benchmark tasks, ACE accurately predicts cost and provides predictive simulations that are closer to synthetic observations than other SBI methods.
- Score: 11.375835331641548
- License: http://creativecommons.org/licenses/by-nc-sa/4.0/
- Abstract: Simulation-based inference (SBI) enables amortized Bayesian inference for
simulators with implicit likelihoods. But when we are primarily interested in
the quality of predictive simulations, or when the model cannot exactly
reproduce the observed data (i.e., is misspecified), targeting the Bayesian
posterior may be overly restrictive. Generalized Bayesian Inference (GBI) aims
to robustify inference for (misspecified) simulator models, replacing the
likelihood-function with a cost function that evaluates the goodness of
parameters relative to data. However, GBI methods generally require running
multiple simulations to estimate the cost function at each parameter value
during inference, making the approach computationally infeasible for even
moderately complex simulators. Here, we propose amortized cost estimation (ACE)
for GBI to address this challenge: We train a neural network to approximate the
cost function, which we define as the expected distance between simulations
produced by a parameter and observed data. The trained network can then be used
with MCMC to infer GBI posteriors for any observation without running
additional simulations. We show that, on several benchmark tasks, ACE
accurately predicts cost and provides predictive simulations that are closer to
synthetic observations than other SBI methods, especially for misspecified
simulators. Finally, we apply ACE to infer parameters of the Hodgkin-Huxley
model given real intracellular recordings from the Allen Cell Types Database.
ACE identifies better data-matching parameters while being an order of
magnitude more simulation-efficient than a standard SBI method. In summary, ACE
combines the strengths of SBI methods and GBI to perform robust and
simulation-amortized inference for scientific simulators.
Related papers
- NAVSIM: Data-Driven Non-Reactive Autonomous Vehicle Simulation and Benchmarking [65.24988062003096]
We present NAVSIM, a framework for benchmarking vision-based driving policies.
Our simulation is non-reactive, i.e., the evaluated policy and environment do not influence each other.
NAVSIM enabled a new competition held at CVPR 2024, where 143 teams submitted 463 entries, resulting in several new insights.
arXiv Detail & Related papers (2024-06-21T17:59:02Z) - Preconditioned Neural Posterior Estimation for Likelihood-free Inference [5.651060979874024]
We show in this paper that the neural posterior estimator (NPE) methods are not guaranteed to be highly accurate, even on problems with low dimension.
We propose preconditioned NPE and its sequential version (PSNPE), which uses a short run of ABC to effectively eliminate regions of parameter space that produce large discrepancy between simulations and data.
We present comprehensive empirical evidence that this melding of neural and statistical SBI methods improves performance over a range of examples.
arXiv Detail & Related papers (2024-04-21T07:05:38Z) - All-in-one simulation-based inference [19.41881319338419]
We present a new amortized inference method -- the Simformer -- which overcomes current limitations.
The Simformer outperforms current state-of-the-art amortized inference approaches on benchmark tasks.
It can be applied to models with function-valued parameters, it can handle inference scenarios with missing or unstructured data, and it can sample arbitrary conditionals of the joint distribution of parameters and data.
arXiv Detail & Related papers (2024-04-15T10:12:33Z) - Diffusion posterior sampling for simulation-based inference in tall data settings [53.17563688225137]
Simulation-based inference ( SBI) is capable of approximating the posterior distribution that relates input parameters to a given observation.
In this work, we consider a tall data extension in which multiple observations are available to better infer the parameters of the model.
We compare our method to recently proposed competing approaches on various numerical experiments and demonstrate its superiority in terms of numerical stability and computational cost.
arXiv Detail & Related papers (2024-04-11T09:23:36Z) - Amortized Bayesian Decision Making for simulation-based models [11.375835331641548]
We address the question of how to perform Bayesian decision making on simulators.
Our method trains a neural network on simulated data and can predict the expected cost.
We then apply the method to infer optimal actions in a real-world simulator in the medical neurosciences.
arXiv Detail & Related papers (2023-12-05T11:29:54Z) - Calibrating Neural Simulation-Based Inference with Differentiable
Coverage Probability [50.44439018155837]
We propose to include a calibration term directly into the training objective of the neural model.
By introducing a relaxation of the classical formulation of calibration error we enable end-to-end backpropagation.
It is directly applicable to existing computational pipelines allowing reliable black-box posterior inference.
arXiv Detail & Related papers (2023-10-20T10:20:45Z) - Simulation-based inference using surjective sequential neural likelihood
estimation [50.24983453990065]
Surjective Sequential Neural Likelihood estimation is a novel method for simulation-based inference.
By embedding the data in a low-dimensional space, SSNL solves several issues previous likelihood-based methods had when applied to high-dimensional data sets.
arXiv Detail & Related papers (2023-08-02T10:02:38Z) - Neural Posterior Estimation with Differentiable Simulators [58.720142291102135]
We present a new method to perform Neural Posterior Estimation (NPE) with a differentiable simulator.
We demonstrate how gradient information helps constrain the shape of the posterior and improves sample-efficiency.
arXiv Detail & Related papers (2022-07-12T16:08:04Z) - Inverting brain grey matter models with likelihood-free inference: a
tool for trustable cytoarchitecture measurements [62.997667081978825]
characterisation of the brain grey matter cytoarchitecture with quantitative sensitivity to soma density and volume remains an unsolved challenge in dMRI.
We propose a new forward model, specifically a new system of equations, requiring a few relatively sparse b-shells.
We then apply modern tools from Bayesian analysis known as likelihood-free inference (LFI) to invert our proposed model.
arXiv Detail & Related papers (2021-11-15T09:08:27Z) - Optimization of High-dimensional Simulation Models Using Synthetic Data [0.1529342790344802]
We introduce the BuB simulator, which requires only the specification of plausible intervals for the simulation parameters.
A detailed statistical analysis can be performed, which allows deep insights into the most important model parameters.
The study explicitly covers difficulties caused by the COVID-19 pandemic.
arXiv Detail & Related papers (2020-09-06T17:21:41Z) - SBI -- A toolkit for simulation-based inference [0.0]
Simulation-based inference ( SBI) seeks to identify parameter sets that a) are compatible with prior knowledge and b) match empirical observations.
We present $textttsbi$, a PyTorch-based package that implements SBI algorithms based on neural networks.
arXiv Detail & Related papers (2020-07-17T16:53:51Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.