Mining gold from implicit models to improve likelihood-free inference

DOI10.1073/pnas.1915980117zbMath1461.62043arXiv1805.12244OpenAlexW3006943238WikidataQ89808324 ScholiaQ89808324MaRDI QIDQ5854829

G. Louppe, Kyle Cranmer, Juan Pavez, Johann Brehmer

Publication date: 12 March 2021

Published in: Proceedings of the National Academy of Sciences (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1805.12244

zbMATH Keywords

likelihood-free inferenceimplicit model

Mathematics Subject Classification ID

Nonparametric estimation (62G05) Implicit function theorems; global Newton methods on manifolds (58C15)

Related Items

Lossless, scalable implicit likelihood inference for cosmological fields ⋮ Robust Approximate Bayesian Inference With Synthetic Likelihood ⋮ The frontier of simulation-based inference ⋮ Unnamed Item ⋮ Analytic auto-differentiable ΛCDM cosmography ⋮ INFERNO: inference-aware neural optimisation ⋮ Bagged Filters for Partially Observed Interacting Systems ⋮ Parametrized classifiers for optimal EFT sensitivity

Uses Software

• Stan
• GitHub
• Pyro
• carl
• NICE
• FFJORD
• Glow
• torchdiffeq
• MADE
• NADE
• WaveNet

Cites Work

• Unnamed Item
• Unnamed Item
• The automated computation of tree-level and next-to-leading order differential cross sections, and their matching to parton shower simulations
• Bayesianly justifiable and relevant frequency calculations for the applied statistician
• Asymptotically exact inference in differentiable generative models
• Likelihood-free inference via classification
• Simple statistical gradient-following algorithms for connectionist reinforcement learning
• Handbook of Approximate Bayesian Computation
• Sequential Monte Carlo without likelihoods
• The Large-Sample Distribution of the Likelihood Ratio for Testing Composite Hypotheses