Interaction decomposition for Hilbert spaces
Gr\'egoire Sergeant-Perthuis

TL;DR
This paper introduces a unified framework for interaction decomposition in Hilbert spaces, extending concepts from graphical models and statistical physics to a categorical setting.
Contribution
It defines and characterizes decomposable functors from posets to Hilbert spaces, unifying and extending existing interaction decompositions.
Findings
Unified framework for interaction decomposition in Hilbert spaces
Extension of previous work on decomposable collections and presheaves
Characterization of decomposable functors from posets to Hilbert spaces
Abstract
The decomposition into interaction subspaces is an important result for graphical models and plays a central role for results on the linearized marginal problem; similarly the Chaos decomposition plays an important role in statistical physics at the thermodynamic limit and in probability theory in general. We unify and extend both constructions by defining and characterizing decomposable functors from a well-founded poset to the category of Hilbert spaces, completing previous work on decomposable collections of vector subspaces and presheaves.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsTopological and Geometric Data Analysis · Bayesian Modeling and Causal Inference · Algebraic structures and combinatorial models
