Differentiable user models

Alex Hämäläinen, Mustafa Mert Celikok, Samuel Kaski

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

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.
Original languageEnglish
Title of host publicationProceedings of the 39th Conference on Uncertainty in Artificial Intelligence (UAI 2023)
PublisherJournal of Machine Learning Research
Pages798-808
Number of pages11
Volume216
Publication statusPublished - 4 Aug 2023
EventConference on Uncertainty in Artificial Intelligence -
Duration: 31 Jul 20234 Aug 2023

Conference

ConferenceConference on Uncertainty in Artificial Intelligence
Period31/07/234/08/23

Fingerprint

Dive into the research topics of 'Differentiable user models'. Together they form a unique fingerprint.

Cite this