A Likelihood-Free Inference Framework for Population Genetic Data using Exchangeable Neural Networks 2021-07-02

Toward a theory of optimization for over-parameterized systems of non-linear equations: the lessons of deep learning 2020-12-07

MetFlow: A New Efficient Method for Bridging the Gap between Markov Chain Monte Carlo and Variational Inference 2020-06-02

Expectation Backpropagation: Parameter-Free Training of Multilayer Neural Networks with Continuous or Discrete Weights 2020-04-14

Partially Exchangeable Networks and Architectures for Learning Summary Statistics in Approximate Bayesian Computation 2020-04-07