English
Related papers

Related papers: A Category of Probability Spaces

200 papers

We study a generalization of the Svarc genus of a fiber map. For an arbitrary collection E of spaces and a map f:X-->Y, we define a numerical invariant, the E-sectional category of f, in terms of open covers of Y. We obtain several basic…

Algebraic Topology · Mathematics 2007-05-23 Martin Arkowitz , Jeffrey Strom

We propose and analyze a novel theoretical and algorithmic framework for structured prediction. While so far the term has referred to discrete output spaces, here we consider more general settings, such as manifolds or spaces of probability…

Machine Learning · Statistics 2020-02-14 Carlo Ciliberto , Lorenzo Rosasco , Alessandro Rudi

In this paper we propose and lay the foundations of a functorial framework for representing signals. By incorporating additional category-theoretic relative and generative perspective alongside the classic set-theoretic measure theory the…

Signal Processing · Electrical Eng. & Systems 2017-10-30 Salil Samant , Shiv Dutt Joshi

Based on previous work of Paul Ressel and myself, I show that the space of all "continuous" exchangeable probability measures on a certain set of order processes is a Bauer simplex.

Probability · Mathematics 2007-05-23 Ulrich Hirth

We present a novel proof of de Finetti's Theorem characterizing permutation-invariant probability measures of infinite sequences of variables, so-called exchangeable measures. The proof is phrased in the language of Markov categories, which…

Probability · Mathematics 2021-11-08 Tobias Fritz , Tomáš Gonda , Paolo Perrone

What does it mean for an algorithm to be fair? Different papers use different notions of algorithmic fairness, and although these appear internally consistent, they also seem mutually incompatible. We present a mathematical setting in which…

Computers and Society · Computer Science 2016-09-26 Sorelle A. Friedler , Carlos Scheidegger , Suresh Venkatasubramanian

We want to replace categories, functors and natural transformations by categories, open functors and open natural transformations. In analogy with open dynamical systems, the adjective open is added here to mean that some external…

Category Theory · Mathematics 2021-02-17 Alexandre Fernandez , Luidnel Maignan , Antoine Spicher

Here, we present a subcategory pEff of Hyland's Effective Topos Eff which can be considered a predicative variant of Eff itself. The construction of pEff is motivated by the desire of providing a "predicative" categorical universe of…

Logic · Mathematics 2018-06-25 Maria Emilia Maietti , Samuele Maschio

Probability theory can be studied synthetically as the computational effect embodied by a commutative monad. In the recently proposed Markov categories, one works with an abstraction of the Kleisli category and then defines deterministic…

Logic in Computer Science · Computer Science 2022-12-06 Sean Moss , Paolo Perrone

Three events in a probability space form a conjunctive fork if they satisfy specific constraints on conditional independence and covariances. Patterns of conjunctive forks within collections of events are characterized by means of systems…

Probability · Mathematics 2016-08-30 Vašek Chvátal , František Matúš , Yori Zwólš

Graduated locally finitely presentable categories are introduced, examples include categories of sets, vector spaces, posets, presheaves and Boolean algebras. A finitary functor between graduated locally finitely presentable categories is…

Category Theory · Mathematics 2024-02-06 Jirí Adámek , Lurdes Sousa

It is shown that every concretizable category can be fully embedded into the category of accessible set functors and natural transformations.

Category Theory · Mathematics 2019-09-12 Libor Barto

Conformal prediction (CP) produces prediction regions with finite-sample, distribution free coverage guarantees, but its interpretation as a quantitative uncertainty tool is often left implicit. We develop a category-theoretic approach that…

Machine Learning · Statistics 2026-05-05 Michele Caprio

In "Frobenius Categories versus Brauer Blocks" we have proved some universality of the so-called localizing functor associated with a Frobenius $P$-category $F$, where $P$ is a finite $p$-group, with respect to the coherent $F$-localities…

Group Theory · Mathematics 2020-03-09 Lluis Puig

Many mathematical objects can be represented as functors from finitely-presented categories $\mathsf{C}$ to $\mathsf{Set}$. For instance, graphs are functors to $\mathsf{Set}$ from the category with two parallel arrows. Such functors are…

Category Theory · Mathematics 2024-08-07 Evan Patterson , Owen Lynch , James Fairbanks

Factor analysis refers to a statistical model in which observed variables are conditionally independent given fewer hidden variables, known as factors, and all the random variables follow a multivariate normal distribution. The parameter…

Statistics Theory · Mathematics 2010-03-04 Mathias Drton , Bernd Sturmfels , Seth Sullivant

Reasoning with defeasible and conflicting knowledge in an argumentative form is a key research field in computational argumentation. Reasoning under various forms of uncertainty is both a key feature and a challenging barrier for automated…

Artificial Intelligence · Computer Science 2024-07-09 Andrei Popescu , Johannes P. Wallner

There are many category-theoretic notions of algebraic theory, including Lawvere theories, monads, PROPs and operads. The first central notion of this thesis is a common generalisation of these, which we call a proto-theory. In order to…

Category Theory · Mathematics 2017-08-04 Tom Avery

Causal spaces have recently been introduced as a measure-theoretic framework to encode the notion of causality. While it has some advantages over established frameworks, such as structural causal models, the theory is so far only developed…

Statistics Theory · Mathematics 2024-06-07 Simon Buchholz , Junhyung Park , Bernhard Schölkopf

Predictive inference is a fundamental task in statistics, traditionally addressed using parametric assumptions about the data distribution and detailed analyses of how models learn from data. In recent years, conformal prediction has…

Methodology · Statistics 2026-03-26 Matteo Sesia , Stefano Favaro