Reference : Adversarial Variational Optimization of Non-Differentiable Simulators
Scientific congresses and symposiums : Paper published in a book
Engineering, computing & technology : Computer science
http://hdl.handle.net/2268/226046
Adversarial Variational Optimization of Non-Differentiable Simulators
English
Louppe, Gilles mailto [Université de Liège - ULiège > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Big Data >]
Hermans, Joeri [Université de Liège - ULiège > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Big Data >]
Cranmer, Kyle []
Apr-2019
Proceedings of Machine Learning Research
Volume 89: The 22nd International Conference on Artificial Intelligence and Statistics, 16-18 April 2019,
Yes
International
AISTATS 2019
April 16-18, 2019
Okinawa
Japan
[en] Statistics - Machine Learning ; Computer Science - Learning
[en] Complex computer simulators are increasingly used across fields of science as generative models tying parameters of an underlying theory to experimental observations. Inference in this setup is often difficult, as simulators rarely admit a tractable density or likelihood function. We introduce Adversarial Variational Optimization (AVO), a likelihood-free inference algorithm for fitting a non-differentiable generative model incorporating ideas from generative adversarial networks, variational optimization and empirical Bayes. We adapt the training procedure of Wasserstein GANs by replacing the differentiable generative network with a domain-specific simulator. We solve the resulting non-differentiable minimax problem by minimizing variational upper bounds of the two adversarial objectives. Effectively, the procedure results in learning a proposal distribution over simulator parameters, such that the Wasserstein distance between the marginal distribution of the synthetic data and the empirical distribution of observed data is minimized. We present results of the method with simulators producing both discrete and continuous data.
Researchers
http://hdl.handle.net/2268/226046
https://arxiv.org/abs/1707.07113

File(s) associated to this reference

Fulltext file(s):

FileCommentaryVersionSizeAccess
Open access
1707.07113.pdfAuthor preprint374.72 kBView/Open

Bookmark and Share SFX Query

All documents in ORBi are protected by a user license.