Skip to content Skip to navigation
University of Warwick
  • Study
  • |
  • Research
  • |
  • Business
  • |
  • Alumni
  • |
  • News
  • |
  • About

University of Warwick
Publications service & WRAP

Highlight your research

  • WRAP
    • Home
    • Search WRAP
    • Browse by Warwick Author
    • Browse WRAP by Year
    • Browse WRAP by Subject
    • Browse WRAP by Department
    • Browse WRAP by Funder
    • Browse Theses by Department
  • Publications Service
    • Home
    • Search Publications Service
    • Browse by Warwick Author
    • Browse Publications service by Year
    • Browse Publications service by Subject
    • Browse Publications service by Department
    • Browse Publications service by Funder
  • Help & Advice
University of Warwick

The Library

  • Login
  • Admin

Robust Bayesian inference for simulator-based models via the MMD posterior bootstrap

Tools
- Tools
+ Tools

Dellaporta, Charita, Knoblauch, Jeremias, Damoulas, Theodoros and Briol, François-Xavier (2022) Robust Bayesian inference for simulator-based models via the MMD posterior bootstrap. In: 25th International Conference in Artificial Intelligence and Statistics (AISTATS), Virtual, 28-30 Mar 2022. Published in: Proceedings of Machine Learning Research, 151 ISSN 2640-3498. (In Press)

[img]
Preview
PDF
WRAP-robust-Bayesian-inference-simulator-based-models-via-the-MMD-posterior-bootstrap-Dellaporta-2022.pdf - Accepted Version - Requires a PDF viewer.

Download (1263Kb) | Preview

Request Changes to record.

Abstract

This paper responds to recent calls to further incorporate the study of animal healthcare into the sociology of health and illness. It focuses on a theme with a long tradition in medical sociology, namely clinical communication, but explores matters distinctive to veterinary practice. Drawing on video recordings of 60 consultations across three small animal veterinary clinics in the UK, we explore how clients and veterinarians (or ‘vets’) fashion fleeting “coalitions of touch”, that aptly position the animal to enable the performance of medical work, often in the face of physical resistance. Building on recent developments in the study of haptic sociality, we analyse how care and emotional concern for animal patients is communicated through various forms of embodied action; thus, how the problematics of forced care and restraint are mitigated through distinctive ways of touching and holding animal patients. Moreover, while prior studies of small animal veterinary work have highlighted the significance of talk within the clinician-animal-client triad, we reveal the fundamentally embodied and collaborative work of managing and controlling patients during sometimes intense and fast-moving episodes of veterinary care. Simulator-based models are models for which the likelihood is intractable but simulation of synthetic data is possible. They are often used to describe complex real-world phenomena, and as such can often be misspecified in practice. Unfortunately, existing Bayesian approaches for simulators are known to perform poorly in those cases. In this paper, we propose a novel algorithm based on the posterior bootstrap and maximum mean discrepancy estimators. This leads to a highly-parallelisable Bayesian inference algorithm with strong robustness properties. This is demonstrated through an in-depth theoretical study which includes generalisation bounds and proofs of frequentist consistency and robustness of our posterior. The approach is then assessed on a range of examples including a g-and-k distribution and a toggle-switch model.

Item Type: Conference Item (Paper)
Subjects: Q Science > QA Mathematics
Divisions: Faculty of Science, Engineering and Medicine > Science > Computer Science
Faculty of Science, Engineering and Medicine > Science > Statistics
Library of Congress Subject Headings (LCSH): Bayesian statistical decision theory, Bootstrap (Statistics), Machine learning -- Statistical methods, Bootstrap (Computer program)
Journal or Publication Title: Proceedings of Machine Learning Research
Publisher: ML Research Press
ISSN: 2640-3498
Official Date: 2022
Dates:
DateEvent
2022Available
18 January 2022Accepted
Volume: 151
Status: Peer Reviewed
Publication Status: In Press
Access rights to Published version: Restricted or Subscription Access
Date of first compliant deposit: 15 February 2022
Date of first compliant Open Access: 18 February 2022
RIOXX Funder/Project Grant:
Project/Grant IDRIOXX Funder NameFunder ID
EP/T51794X/1[EPSRC] Engineering and Physical Sciences Research Councilhttp://dx.doi.org/10.13039/501100000266
UNSPECIFIEDBiometrika Trusthttp://viaf.org/viaf/155095034
EP/V02678X/1UK Research and Innovationhttp://dx.doi.org/10.13039/100014013
EP/N510129/1Lloyd's Register Foundationhttp://dx.doi.org/10.13039/100008885
EP/N510129/1Alan Turing Institutehttp://dx.doi.org/10.13039/100012338
Conference Paper Type: Paper
Title of Event: 25th International Conference in Artificial Intelligence and Statistics (AISTATS)
Type of Event: Conference
Location of Event: Virtual
Date(s) of Event: 28-30 Mar 2022
Related URLs:
  • Organisation
  • Organisation
  • Publisher
Open Access Version:
  • ArXiv

Request changes or add full text files to a record

Repository staff actions (login required)

View Item View Item

Downloads

Downloads per month over past year

View more statistics

twitter

Email us: wrap@warwick.ac.uk
Contact Details
About Us