The process of inverting Markov kernels relates to the important subject of Bayesian modelling and learning. In fact, Bayesian update is exactly kernel inversion. In this paper, we investigate how and when Markov kernels (aka stochastic relations, or probabilistic mappings, or simply kernels) can be inverted. We address the question both directly on the category of measurable spaces, and indirectly by interpreting kernels as Markov operators: For the direct option, we introduce a typed versio...Expand abstract
- Publication status:
- Peer review status:
- Peer reviewed
- Version of record
- Schloss Dagstuhl - Leibniz-Zentrum für Informatik Publisher's website
- Publication date:
- Pubs id:
- Local pid:
- Copyright holder:
- Dahlqvist et al.
- Copyright date:
© Fredrik Dahlqvist, Vincent Danos, Ilias Garnier, and Ohad Kammar;
licensed under Creative Commons License CC-BY
This is a conference paper from 27th International Conference on Concurrency Theory (CONCUR 2016).