Pointless learning (long version)

Resource type
Authors/contributors
Title
Pointless learning (long version)
Abstract
Bayesian inversion is at the heart of probabilistic programming and more generally machine learning. Understanding inversion is made difficult by the pointful (kernel-centric) point of view usually taken in the literature. We develop a pointless (kernel-free) approach to inversion. While doing so, we revisit some foundational objects of probability theory, unravel their category-theoretical underpinnings and show how pointless Bayesian inversion sits naturally at the centre of this construction .
Date
January 2017
Accessed
2019-11-24T12:02:56Z
Library Catalog
HAL Archives Ouvertes
Extra
ZSCC: 0000000
Notes

Accepted to the 20th International Conference on Foundations of Software Science and Computation Structures (FoSSaCS) (pre-proceedings version)

Citation
Clerc, F., Danos, V., Dahlqvist, F., & Garnier, I. (2017). Pointless learning (long version). Retrieved from https://hal.archives-ouvertes.fr/hal-01429663
Processing time: 0.01 seconds

Graph of references

(from Zotero to Gephi via Zotnet with this script)
Graph of references