Inference compilation and universal probabilistic programming

We introduce a method for using deep neural networks to amortize the cost of inference in models from the family induced by universal probabilistic programming languages, establishing a framework that combines the strengths of probabilistic programming and deep learning methods. We call what we do “...

وصف كامل

التفاصيل البيبلوغرافية
المؤلفون الرئيسيون: Le, T, Baydin, A, Wood, F
التنسيق: Conference item
منشور في: Journal of Machine Learning Research 2017

مواد مشابهة