Faithful inversion of generative models for effective amortized inference

Inference amortization methods share information across multiple posteriorinference problems, allowing each to be carried out more efficiently. Generally, they require the inversion of the dependency structure in the generative model, as the modeller must learn a mapping from observations to distrib...

詳細記述

書誌詳細
主要な著者: Webb, S, Golinski, A, Zinkov, R, Narayanaswamy, S, Rainforth, T, Teh, Y, Wood, F
フォーマット: Conference item
出版事項: Curran Associates 2019