| CARVIEW |
Select Language
HTTP/2 200
server: GitHub.com
content-type: text/html; charset=utf-8
last-modified: Wed, 03 Dec 2025 19:31:30 GMT
access-control-allow-origin: *
strict-transport-security: max-age=31556952
etag: W/"69309012-137a"
expires: Sun, 28 Dec 2025 17:49:35 GMT
cache-control: max-age=600
content-encoding: gzip
x-proxy-cache: MISS
x-github-request-id: F0BE:292AC1:7DA339:8CE60E:69516B57
accept-ranges: bytes
age: 0
date: Sun, 28 Dec 2025 17:39:35 GMT
via: 1.1 varnish
x-served-by: cache-bom-vanm7210093-BOM
x-cache: MISS
x-cache-hits: 0
x-timer: S1766943575.405353,VS0,VE202
vary: Accept-Encoding
x-fastly-request-id: 58881b4a976571af02c595db53742b01deb2540c
content-length: 1815
Michael U. Gutmann 
Michael U. Gutmann
I am a Senior Lecturer (Assoc Prof) in Machine Learning at the School of Informatics of the University of Edinburgh, affiliated with the Institute for Adaptive & Neural Computation.
My research is in machine learning for science, with a focus on developing methods for (Bayesian) inference and design.
A short biography is available here.
Recent papers
NeurIPS: Neural Mutual Information Estimation with Vector Copulas [link]
arXiv: CFMI: Flow Matching for Missing Data Imputation [link]
arXiv: Simulation-based Bayesian inference under model misspecification [link]
BioRxiv: Risk-averse optimization of genetic circuits under uncertainty [link]
TMLR: Improving Variational Autoencoder Estimation from Incomplete Data with Mixture Variational Families [link]
CC BY-SA 4.0 Michael U. Gutmann. Last modified: December 03, 2025. Accessibility. Website built with Franklin.jl and the Julia programming language.