Likelihood-Free Inference with Generative Neural Networks via Scoring Rule Minimization

  title={Likelihood-Free Inference with Generative Neural Networks via Scoring Rule Minimization},
  author={Lorenzo Pacchiardi and Ritabrata Dutta},
Bayesian Likelihood-Free Inference methods yield posterior approximations for simulator models with intractable likelihood. Recently, many works trained neural networks to approximate either the intractable likelihood or the posterior directly. Most proposals use normalizing flows, namely neural networks parametrizing invertible maps used to transform samples from an underlying base measure; the probability density of the transformed samples is then accessible and the normalizing flow can be… 


Probabilistic Forecasting with Conditional Generative Networks via Scoring Rule Minimization
This manuscript performs probabilistic forecasting with conditional generative networks trained to minimize scoring rule values on two chaotic models and a global dataset of weather observations; results are satisfactory and better calibrated than what achieved by GANs.
f-GAN: Training Generative Neural Samplers using Variational Divergence Minimization
It is shown that any f-divergence can be used for training generative neural samplers and the benefits of various choices of divergence functions on training complexity and the quality of the obtained generative models are discussed.
Generative Adversarial Nets
We propose a new framework for estimating generative models via an adversarial process, in which we simultaneously train two models: a generative model G that captures the data distribution, and a
Auto-Encoding Variational Bayes
A stochastic variational inference and learning algorithm that scales to large datasets and, under some mild differentiability conditions, even works in the intractable case is introduced.
GATSBI: Generative Adversarial Training for Simulation-Based Inference
GATSBI opens up opportunities for leveraging advances in GANs to perform Bayesian inference on high-dimensional simulation-based models, and shows how GATSBI can be extended to perform sequential posterior estimation to focus on individual observations.
BayesFlow: Learning Complex Stochastic Models With Invertible Neural Networks
It is argued that BayesFlow provides a general framework for building amortized Bayesian parameter estimation machines for any forward model from which data can be simulated and is applicable to modeling scenarios where standard inference techniques with handcrafted summary statistics fail.
Automatic Posterior Transformation for Likelihood-Free Inference
Automatic posterior transformation (APT) is presented, a new sequential neural posterior estimation method for simulation-based inference that can modify the posterior estimate using arbitrary, dynamically updated proposals, and is compatible with powerful flow-based density estimators.
Flexible statistical inference for mechanistic models of neural dynamics
This work builds on recent advances in ABC by learning a neural network which maps features of the observed data to the posterior distribution over parameters, and learns a Bayesian mixture-density network approximating the posterior over multiple rounds of adaptively chosen simulations.
MMD-Bayes: Robust Bayesian Estimation via Maximum Mean Discrepancy
A pseudo-likelihood based on the Maximum Mean Discrepancy, defined via an embedding of probability distributions into a reproducing kernel Hilbert space is built, and it is shown that this MMD-Bayes posterior is consistent and robust to model misspecification.
Bayesian Synthetic Likelihood
The accuracy and computational efficiency of the Bayesian version of the synthetic likelihood (BSL) approach is explored in comparison to a competitor known as approximate Bayesian computation (ABC) and its sensitivity to its tuning parameters and assumptions.