Amortised Experimental Design and Parameter Estimation for User Models of Pointing

Antti Keurulainen, Isak Rafael Westerlund, Oskar Keurulainen, Andrew Howes

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

1 Citation (Scopus)
36 Downloads (Pure)

Abstract

User models play an important role in interaction design, supporting automation of interaction design choices. In order to do so, model parameters must be estimated from user data. While very large amounts of user data are sometimes required, recent research has shown how experiments can be designed so as to gather data and infer parameters as efficiently as possible, thereby minimising the data requirement. In the current article, we investigate a variant of these methods that amortises the computational cost of designing experiments by training a policy for choosing experimental designs with simulated participants. Our solution learns which experiments provide the most useful data for parameter estimation by interacting with in-silico agents sampled from the model space thereby using synthetic data rather than vast amounts of human data. The approach is demonstrated for three progressively complex models of pointing.

Original languageEnglish
Title of host publicationCHI 2023 - Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems
PublisherACM
ISBN (Electronic)978-1-4503-9421-5
DOIs
Publication statusPublished - 19 Apr 2023
MoE publication typeA4 Conference publication
EventACM SIGCHI Annual Conference on Human Factors in Computing Systems - Hamburg, Germany
Duration: 23 Apr 202328 Apr 2023
https://chi2023.acm.org/

Conference

ConferenceACM SIGCHI Annual Conference on Human Factors in Computing Systems
Abbreviated titleACM CHI
Country/TerritoryGermany
CityHamburg
Period23/04/202328/04/2023
Internet address

Keywords

  • active inference
  • adaptive experiment design
  • computational rationality
  • parameter estimation
  • user models

Fingerprint

Dive into the research topics of 'Amortised Experimental Design and Parameter Estimation for User Models of Pointing'. Together they form a unique fingerprint.

Cite this