Differentiable user models
| dc.contributor | Aalto-yliopisto | fi |
| dc.contributor | Aalto University | en |
| dc.contributor.author | Hämäläinen, Alex | en_US |
| dc.contributor.author | Celikok, Mustafa Mert | en_US |
| dc.contributor.author | Kaski, Samuel | en_US |
| dc.contributor.department | Department of Computer Science | en |
| dc.contributor.groupauthor | Probabilistic Machine Learning | en |
| dc.contributor.groupauthor | Professorship Kaski Samuel | en |
| dc.contributor.groupauthor | Computer Science Professors | en |
| dc.contributor.groupauthor | Computer Science - Artificial Intelligence and Machine Learning (AIML) | en |
| dc.contributor.groupauthor | Finnish Center for Artificial Intelligence, FCAI | en |
| dc.contributor.groupauthor | Helsinki Institute for Information Technology (HIIT) | en |
| dc.date.accessioned | 2023-09-13T06:49:51Z | |
| dc.date.available | 2023-09-13T06:49:51Z | |
| dc.date.issued | 2023-08 | en_US |
| dc.description | | openaire: EC/H2020/951847/EU//ELISE | openaire: EC/H2020/952026/EU//HumanE-AI-Net | |
| dc.description.abstract | Probabilistic user modeling is essential for building machine learning systems in the ubiquitous cases with humans in the loop. However, modern advanced user models, often designed as cognitive behavior simulators, are incompatible with modern machine learning pipelines and computationally prohibitive for most practical applications. We address this problem by introducing widely-applicable differentiable surrogates for bypassing this computational bottleneck; the surrogates enable computationally efficient inference with modern cognitive models. We show experimentally that modeling capabilities comparable to the only available solution, existing likelihood-free inference methods, are achievable with a computational cost suitable for online applications. Finally, we demonstrate how AI-assistants can now use cognitive models for online interaction in a menu-search task, which has so far required hours of computation during interaction. | en |
| dc.description.version | Peer reviewed | en |
| dc.format.extent | 798-808 | |
| dc.format.mimetype | application/pdf | en_US |
| dc.identifier.citation | Hämäläinen, A, Celikok, M M & Kaski, S 2023, Differentiable user models . in Proceedings of the 39th Conference on Uncertainty in Artificial Intelligence (UAI 2023) . vol. 216, Proceedings of Machine Learning Research, vol. 216, JMLR, pp. 798-808, Conference on Uncertainty in Artificial Intelligence, Pittsburgh, Pennsylvania, United States, 31/07/2023 . < https://proceedings.mlr.press/v216/hamalainen23a.html > | en |
| dc.identifier.issn | 2640-3498 | |
| dc.identifier.other | PURE UUID: fb4e5806-6c9f-4359-8599-5c32dc338eb9 | en_US |
| dc.identifier.other | PURE ITEMURL: https://research.aalto.fi/en/publications/fb4e5806-6c9f-4359-8599-5c32dc338eb9 | en_US |
| dc.identifier.other | PURE LINK: http://www.scopus.com/inward/record.url?scp=85170073638&partnerID=8YFLogxK | en_US |
| dc.identifier.other | PURE LINK: https://proceedings.mlr.press/v216/hamalainen23a.html | en_US |
| dc.identifier.other | PURE FILEURL: https://research.aalto.fi/files/120701468/SCI_H_m_l_inen_etal_UAI_2023.pdf | en_US |
| dc.identifier.uri | https://aaltodoc.aalto.fi/handle/123456789/123524 | |
| dc.identifier.urn | URN:NBN:fi:aalto-202309135884 | |
| dc.language.iso | en | en |
| dc.publisher | PMLR | |
| dc.relation | info:eu-repo/grantAgreement/EC/H2020/952026/EU//HumanE-AI-Net | en_US |
| dc.relation.ispartof | Conference on Uncertainty in Artificial Intelligence | en |
| dc.relation.ispartofseries | Proceedings of the 39th Conference on Uncertainty in Artificial Intelligence (UAI 2023) | en |
| dc.relation.ispartofseries | Proceedings of Machine Learning Research | en |
| dc.relation.ispartofseries | Volume 216 | en |
| dc.rights | openAccess | en |
| dc.title | Differentiable user models | en |
| dc.type | Conference article in proceedings | fi |
| dc.type.version | publishedVersion |
