6 Lataukset (Pure)

Abstrakti

In machine learning and computer vision, optimal transport has had significant success in learning generative models and defining metric distances between structured and stochastic data objects, that can be cast as probability measures.
The key element of optimal transport is the so called lifting of an exact cost (distance) function, defined on the sample space, to a cost (distance) between probability measures over the sample space. However, in many real life applications the cost is stochastic: e.g., the unpredictable traffic flow affects the cost of transportation between a factory and an outlet. To take this stochasticity into account, we introduce a Bayesian framework for inferring the optimal transport plan distribution induced by the stochastic cost, allowing for a principled way to include prior information and to model the induced stochasticity on the transport plans. Additionally, we tailor an HMC method to sample from the resulting transport plan posterior distribution.
AlkuperäiskieliEnglanti
OtsikkoProceedings of Asian Conference on Machine Learning
Sivut1601-1616
Sivumäärä16
TilaJulkaistu - 2021
OKM-julkaisutyyppiA4 Artikkeli konferenssijulkaisuussa
TapahtumaAsian Conference on Machine Learning - Virtual, Online
Kesto: 17 marraskuuta 202119 marraskuuta 2021
Konferenssinumero: 13

Julkaisusarja

NimiProceedings of Machine Learning Research
KustantajaPMLR
Vuosikerta157
ISSN (elektroninen)2640-3498

Conference

ConferenceAsian Conference on Machine Learning
LyhennettäACML
KaupunkiVirtual, Online
Ajanjakso17/11/202119/11/2021

Sormenjälki

Sukella tutkimusaiheisiin 'Bayesian Inference for Optimal Transport with Stochastic Cost'. Ne muodostavat yhdessä ainutlaatuisen sormenjäljen.

Siteeraa tätä