Tailoring to the Tails: Risk Measures for Fine-Grained Tail Sensitivity
Fröhlich, Christian, and Robert C Williamson. 2023. “Tailoring to the Tails: Risk Measures for Fine-Grained Tail Sensitivity”. Transactions on Machine Learning Research.
Search
Search results
84 results found
Random Classification Noise does not defeat All Convex Potential Boosters Irrespective of Model Choice
Mansour, Yishay, Richard Nock, and Robert C. Williamson. 2023. “Random Classification Noise Does Not Defeat All Convex Potential Boosters Irrespective of Model Choice”. In ICML2023 .
Corruptions of Supervised Learning Problems: Typology and Mitigations
Iacovissi, Laura, Nan Lu, and Robert C. Williamson. 2024. “Corruptions of Supervised Learning Problems: Typology and Mitigations”. ArXiv.
Style of Reasoning of Machine Learning
The notion of a "style of reasoning" was developed by Ian Hacking, who explored in particular the statistical style of reasoning in XXX. In this project we build upon that work to analyse the style of reasoning of machine learning. We argue that (ironically) although ML makes great use of data, it...
Bob Williamson
I am professor of foundations of machine learning systems at the University of Tübingen. I am a principal investigator in the Tübingen AI center and a member of the Cluster of Excellence Machine Learning in the Sciences. Current Research My current research is focused on a small number of basic...
The Style of Reasoning of Machine Learning
FMLS Blog
Hello
Christian Fröhlich
Since my undergraduate studies in cognitive science, I have been interested in interdisciplinary research approaches. I started my PhD with Bob in November, 2021. I'm interested in a generalization of classical probability theory known as imprecise probability where one works with sets of...
Slow Science
Machine learning research is notoriously fast paced. Can one get off the treadmill and embrace a notion of slow science? I am pleased to be able to argue yes by example! Recently I have had two works published with a very long gestation. The first Geometry and Calculus of Losses reports work that...