We propose Gaussian Semantics, which approximates the exact probabilistic semantics of a bounded program by means of Gaussian mixtures.

Nov 14, 2023 · We propose Gaussian Semantics, which approximates the exact probabilistic semantics of a bounded program by means of Gaussian mixtures. It is ...

A universal approximation theorem stating that, under mild conditions, Gaussian Semantics can approximate the exact semantics arbitrarily closely is ...

It is parametrized by a map that associates each program location with the moment order to be matched in the approximation. We provide two main contributions.

This is the replication package for the paper “Inference of Probabilistic Programs with Moment-Matching Gaussian Mixtures”

Oct 17, 2024 · , Mirco Tribastone : Inference of Probabilistic Programs with Moment-Matching Gaussian Mixtures. Proc. ACM Program. Lang. 8(POPL): 1882-1912 ...

Nov 21, 2023 · My new paper, titled 'Can an unsupervised clustering algorithm reproduce a categorization system?', is out on arXiv now. My coauthors are ...

We study semantic models of probabilistic programming languages over graphs, and establish a connection to graphons from graph theory and combinatorics.

This seminar covers a variety of topics in the field of probabilistic programs. Roughly speaking, probabilistic programs are like ordinary programs, with an ...

Duration: 18:40
Posted: Mar 20, 2024