Conference item
Continual repeated annealed flow transport Monte Carlo
- Abstract:
-
We propose Continual Repeated Annealed Flow Transport Monte Carlo (CRAFT), a method that combines a sequential Monte Carlo (SMC) sampler (itself a generalization of Annealed Importance Sampling) with variational inference using normalizing flows. The normalizing flows are directly trained to transport between annealing temperatures using a KL divergence for each transition. This optimization objective is itself estimated using the normalizing flow/SMC approximation. We show conceptually and u...
Expand abstract
- Publication status:
- Published
- Peer review status:
- Peer reviewed
Actions
Access Document
- Files:
-
-
(Version of record, pdf, 732.4KB)
-
- Publication website:
- https://proceedings.mlr.press/v162/matthews22a.html
Authors
Bibliographic Details
- Publisher:
- Journal of Machine Learning Research Publisher's website
- Host title:
- Proceedings of the 39th International Conference on Machine Learning
- Series:
- Proceedings of Machine Learning Research
- Series number:
- 162
- Pages:
- 15196-15219
- Publication date:
- 2022-06-22
- Acceptance date:
- 2022-05-14
- Event title:
- 39th International Conference on Machine Learning (ICML 2022)
- Event location:
- Baltimore, Maryland, USA
- Event website:
- https://icml.cc/Conferences/2022
- Event start date:
- 2022-07-17
- Event end date:
- 2022-07-23
- ISSN:
-
2640-3498
Item Description
- Language:
- English
- Keywords:
- Pubs id:
-
1312349
- Local pid:
- pubs:1312349
- Deposit date:
- 2022-12-08
Terms of use
- Copyright holder:
- Matthews et al.
- Copyright date:
- 2022
- Rights statement:
- Copyright 2022 by the author(s).
Metrics
If you are the owner of this record, you can report an update to it here: Report update to this record