Optimal Transport for $ε$-Contaminated Credal Sets: To the Memory of Sayan Mukherjee
Fuente:
arXiv
Salvato in:
| Autore principale: | |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910913763737600 |
|---|---|
| author | Caprio, Michele |
| author_facet | Caprio, Michele |
| contents | We present generalized versions of Monge's and Kantorovich's optimal transport problems with the probabilities being transported replaced by lower probabilities. We show that, when the lower probabilities are the lower envelopes of $ε$-contaminated sets, then our version of Monge's, and a restricted version of our Kantorovich's problems, coincide with their respective classical versions. We also give sufficient conditions for the existence of our version of Kantorovich's optimal plan, and for the two problems to be equivalent. As a byproduct, we show that for $ε$-contaminations the lower probability versions of Monge's and Kantorovich's optimal transport problems need not coincide. The applications of our results to Machine Learning and Artificial Intelligence are also discussed. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_03267 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Optimal Transport for $ε$-Contaminated Credal Sets: To the Memory of Sayan Mukherjee Caprio, Michele Machine Learning Probability 49Q22, 68T37, 60A99 We present generalized versions of Monge's and Kantorovich's optimal transport problems with the probabilities being transported replaced by lower probabilities. We show that, when the lower probabilities are the lower envelopes of $ε$-contaminated sets, then our version of Monge's, and a restricted version of our Kantorovich's problems, coincide with their respective classical versions. We also give sufficient conditions for the existence of our version of Kantorovich's optimal plan, and for the two problems to be equivalent. As a byproduct, we show that for $ε$-contaminations the lower probability versions of Monge's and Kantorovich's optimal transport problems need not coincide. The applications of our results to Machine Learning and Artificial Intelligence are also discussed. |
| title | Optimal Transport for $ε$-Contaminated Credal Sets: To the Memory of Sayan Mukherjee |
| topic | Machine Learning Probability 49Q22, 68T37, 60A99 |
| url | https://arxiv.org/abs/2410.03267 |