DeepAI AI Chat
Log In Sign Up

Bayesian Updates Compose Optically

by   Toby St. Clere Smithe, et al.

Bayes' rule tells us how to invert a causal process in order to update our beliefs in light of new evidence. If the process is believed to have a complex compositional structure, we may ask whether composing the inversions of the component processes gives the same belief update as the inversion of the whole. We answer this question affirmatively, showing that the relevant compositional structure is precisely that of the lens pattern, and that we can think of Bayesian inversion as a particular instance of a state-dependent morphism in a corresponding fibred category. We define a general notion of (mixed) Bayesian lens, and discuss the (un)lawfulness of these lenses when their contravariant components are exact Bayesian inversions. We prove our main result both abstractly and concretely, for both discrete and continuous states, taking care to illustrate the common structures.


page 1

page 2

page 3

page 4


The Compositional Structure of Bayesian Inference

Bayes' rule tells us how to invert a causal process in order to update o...

Compositional Active Inference I: Bayesian Lenses. Statistical Games

We introduce the concepts of Bayesian lens, characterizing the bidirecti...

Mathematical Foundations for a Compositional Account of the Bayesian Brain

This dissertation reports some first steps towards a compositional accou...

Dependent Bayesian Lenses: Categories of Bidirectional Markov Kernels with Canonical Bayesian Inversion

We generalise an existing construction of Bayesian Lenses to admit lense...

Cyber Kittens, or Some First Steps Towards Categorical Cybernetics

We define a categorical notion of cybernetic system as a dynamical reali...

Conservative Inference Rule for Uncertain Reasoning under Incompleteness

In this paper we formulate the problem of inference under incomplete inf...

Approximate Inference via Fibrations of Statistical Games

We characterize a number of well known systems of approximate inference ...