The cut metric for probability distributions

05/31/2019
by   Amin Coja-Oghlan, et al.
0

Guided by the theory of graph limits, we investigate a variant of the cut metric for limit objects of sequences of discrete probability distributions. Apart from establishing basic results, we introduce a natural operation called pinning on the space of limit objects and show how this operation yields a canonical cut metric approximation to a given probability distribution akin to the weak regularity lemma for graphons. We also establish the cut metric continuity of basic operations such as taking product measures.

READ FULL TEXT
research
10/31/2017

Algorithmic learning of probability distributions from random data in the limit

We study the problem of identifying a probability distribution for some ...
research
09/11/2023

Generalized Graphon Process: Convergence of Graph Frequencies in Stretched Cut Distance

Graphons have traditionally served as limit objects for dense graph sequ...
research
10/22/2020

Exponential Negation of a Probability Distribution

Negation operation is important in intelligent information processing. D...
research
01/03/2022

A New Modeling of Classical Folds in Computational Origami

This paper shows a cut along a crease on an origami sheet makes simple m...
research
01/05/2018

Equivalences between learning of data and probability distributions, and their applications

Algorithmic learning theory traditionally studies the learnability of ef...
research
01/22/2022

Beyond Nonexpansive Operations in Quantitative Algebraic Reasoning

The framework of quantitative equational logic has been successfully app...
research
06/28/2017

Approximation of probability density functions on the Euclidean group parametrized by dual quaternions

Perception is fundamental to many robot application areas especially in ...

Please sign up or login with your details

Forgot password? Click here to reset