Solving Schrödinger Bridges via Maximum Likelihood.
dc.contributor.author | Vargas, Francisco | |
dc.contributor.author | Thodoroff, Pierre | |
dc.contributor.author | Lamacraft, Austen | |
dc.contributor.author | Lawrence, Neil | |
dc.contributor.orcid | Vargas, Francisco [0000-0002-2714-3357] | |
dc.contributor.orcid | Thodoroff, Pierre [0000-0001-7791-217X] | |
dc.contributor.orcid | Lamacraft, Austen [0000-0002-0707-0488] | |
dc.contributor.orcid | Lawrence, Neil [0000-0001-9258-1030] | |
dc.date.accessioned | 2021-10-30T01:12:50Z | |
dc.date.available | 2021-10-30T01:12:50Z | |
dc.date.issued | 2021-08-31 | |
dc.date.updated | 2021-10-30T01:12:49Z | |
dc.description.abstract | The Schrödinger bridge problem (SBP) finds the most likely stochastic evolution between two probability distributions given a prior stochastic evolution. As well as applications in the natural sciences, problems of this kind have important applications in machine learning such as dataset alignment and hypothesis testing. Whilst the theory behind this problem is relatively mature, scalable numerical recipes to estimate the Schrödinger bridge remain an active area of research. Our main contribution is the proof of equivalence between solving the SBP and an autoregressive maximum likelihood estimation objective. This formulation circumvents many of the challenges of density estimation and enables direct application of successful machine learning techniques. We propose a numerical procedure to estimate SBPs using Gaussian process and demonstrate the practical usage of our approach in numerical simulations and experiments. | |
dc.identifier.citation | Entropy (Basel, Switzerland), volume 23, issue 9 | |
dc.identifier.doi | 10.17863/CAM.77532 | |
dc.identifier.issn | 1099-4300 | |
dc.identifier.other | PMC8464739 | |
dc.identifier.other | 34573759 | |
dc.identifier.uri | https://www.repository.cam.ac.uk/handle/1810/330088 | |
dc.language | eng | |
dc.rights | Attribution 4.0 International | |
dc.rights.uri | https://creativecommons.org/licenses/by/4.0/ | |
dc.source | essn: 1099-4300 | |
dc.source | nlmid: 101243874 | |
dc.subject | Machine Learning | |
dc.subject | Stochastic Control | |
dc.subject | Schrödinger Bridges | |
dc.title | Solving Schrödinger Bridges via Maximum Likelihood. | |
dc.type | Article | |
pubs.funder-project-id | Engineering and Physical Sciences Research Council (EP/T517847/1) | |
pubs.funder-project-id | huawei technology co (NA) | |
rioxxterms.licenseref.uri | https://creativecommons.org/licenses/by/4.0/ | |
rioxxterms.version | VoR | |
rioxxterms.versionofrecord | 10.3390/e23091134 |
Files
Original bundle
1 - 1 of 1
Loading...
- Name:
- article.pdf
- Size:
- 1.5 MB
- Format:
- Adobe Portable Document Format
- Description:
- Published version
- Licence
- https://creativecommons.org/licenses/by/4.0/