Abstract / Description of output
Inference amortization methods share information across multiple posterior-inference 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 distributions approximating the posterior. Previous approaches have involved inverting the dependency structure in a heuristic way that fails to capture these dependencies correctly, thereby limiting the achievable accuracy of the resulting approximations. We introduce an algorithm for faithfully, and minimally, inverting the graphical model structure of any generative model. Such inverses have two crucial properties: (a) they do not encode any independence assertions that are absent from the model and; (b) they are local maxima for the number of true independencies encoded. We prove the correctness of our approach and empirically show that the resulting minimally faithful inverses lead to better inference amortization than existing heuristic approaches.
Original language | English |
---|---|
Title of host publication | Advances in Neural Information Processing Systems 31 |
Editors | S. Bengio, H. Wallach, H. Larochelle, K. Grauman, N. Cesa-Bianchi, R. Garnett |
Publisher | Curran Associates Inc |
Pages | 3070-3080 |
Number of pages | 11 |
Publication status | Published - 8 Dec 2018 |
Event | Thirty-second Conference on Neural Information Processing Systems - Montreal, Canada Duration: 3 Dec 2018 → 8 Dec 2018 https://nips.cc/ |
Conference
Conference | Thirty-second Conference on Neural Information Processing Systems |
---|---|
Abbreviated title | NIPS 2018 |
Country/Territory | Canada |
City | Montreal |
Period | 3/12/18 → 8/12/18 |
Internet address |