Dynamic Likelihood-free Inference via Ratio Estimation (DIRE)

by   Traiko Dinev, et al.

Parametric statistical models that are implicitly defined in terms of a stochastic data generating process are used in a wide range of scientific disciplines because they enable accurate modeling. However, learning the parameters from observed data is generally very difficult because their likelihood function is typically intractable. Likelihood-free Bayesian inference methods have been proposed which include the frameworks of approximate Bayesian computation (ABC), synthetic likelihood, and its recent generalization that performs likelihood-free inference by ratio estimation (LFIRE). A major difficulty in all these methods is choosing summary statistics that reduce the dimensionality of the data to facilitate inference. While several methods for choosing summary statistics have been proposed for ABC, the literature for synthetic likelihood and LFIRE is very thin to date. We here address this gap in the literature, focusing on the important special case of time-series models. We show that convolutional neural networks trained to predict the input parameters from the data provide suitable summary statistics for LFIRE. On a wide range of time-series models, a single neural network architecture produced equally or more accurate posteriors than alternative methods.


page 1

page 2

page 3

page 4


Learning summary features of time series for likelihood free inference

There has been an increasing interest from the scientific community in u...

Approximate Bayesian Computation with Path Signatures

Simulation models of scientific interest often lack a tractable likeliho...

BayesFlow: Learning complex stochastic models with invertible neural networks

Estimating the parameters of mathematical models is a common problem in ...

The Fixed Landscape Inference MethOd (flimo): an alternative to Approximate Bayesian Computation, faster by several orders of magnitude

Modelling in biology must adapt to increasingly complex and massive data...

Nonparametric Time Series Summary Statistics for High-Frequency Actigraphy Data from Individuals with Advanced Dementia

Actigraphy data has been widely used to measure activity and the circadi...

Towards constraining warm dark matter with stellar streams through neural simulation-based inference

A statistical analysis of the observed perturbations in the density of s...

Partially Exchangeable Networks and Architectures for Learning Summary Statistics in Approximate Bayesian Computation

We present a novel family of deep neural architectures, named partially ...

Please sign up or login with your details

Forgot password? Click here to reset