Differentiable User Models

November 29, 2022 Β· Declared Dead Β· πŸ› Conference on Uncertainty in Artificial Intelligence

πŸ‘» CAUSE OF DEATH: Ghosted
No code link whatsoever

"No code URL or promise found in abstract"

Evidence collected by the PWNC Scanner

Authors Alex HΓ€mΓ€lΓ€inen, Mustafa Mert Γ‡elikok, Samuel Kaski arXiv ID 2211.16277 Category cs.LG: Machine Learning Cross-listed cs.AI, cs.HC Citations 3 Venue Conference on Uncertainty in Artificial Intelligence Last Checked 3 months ago
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.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

πŸ“œ Similar Papers

In the same crypt β€” Machine Learning

Died the same way β€” πŸ‘» Ghosted