Probability Theory from a Programming Perspective (Invited Paper)
A leading idea is to apply techniques from verification and programming theory to machine learning and statistics, to deal with things like compositionality and various notions of correctness and complexity. Probabilistic programming is an example of this. Moreover, this approach leads to new foundational methods in probability theory. This is particularly true in the "non-parametric" aspects, for example in higher-order functions and infinite random graph models.
correctness
complexity
statistics
Theory of computation~Computational complexity and cryptography
3:1-3:1
Invited Paper
Sam
Staton
Sam Staton
Department of Computer Science, University of Oxford, Oxford OX1 3QD UK
10.4230/LIPIcs.ICALP.2018.3
Sam Staton
Creative Commons Attribution 3.0 Unported license
https://creativecommons.org/licenses/by/3.0/legalcode