English
Related papers

Related papers: Fair Measures for Countable-to-one Maps

200 papers

We study countably monotone and Markov interval maps. We establish sufficient conditions for uniqueness of a conjugate map of constant slope. We explain how global window perturbation can be used to generate a large class of maps satisfying…

Dynamical Systems · Mathematics 2021-04-07 Samuel Roth

As learning machines increase their influence on decisions concerning human lives, analyzing their fairness properties becomes a subject of central importance. Yet, our best tools for measuring the fairness of learning systems are rigid…

Machine Learning · Statistics 2022-07-21 David Lopez-Paz , Diane Bouchacourt , Levent Sagun , Nicolas Usunier

We revisit the problem of counting the number of copies of a fixed graph in a random graph or multigraph, including the case of constrained degrees. Our approach relies heavily on analytic combinatorics and on the notion of patchwork to…

Discrimination via algorithmic decision making has received considerable attention. Prior work largely focuses on defining conditions for fairness, but does not define satisfactory measures of algorithmic unfairness. In this paper, we focus…

For upper semi-continuous potentials defined on shifts over countable alphabets, this paper ensures sufficient conditions for the existence of a maximizing measure. We resort to the concept of blur shift, introduced by T. Almeida and M.…

Dynamical Systems · Mathematics 2026-04-29 Eduardo Garibaldi , João T A Gomes , Marcelo Sobottka

The pursuit of fairness in machine learning (ML), ensuring that the models do not exhibit biases toward protected demographic groups, typically results in a compromise scenario. This compromise can be explained by a Pareto frontier where…

Machine Learning · Computer Science 2024-11-11 Jinlong Pang , Jialu Wang , Zhaowei Zhu , Yuanshun Yao , Chen Qian , Yang Liu

In this paper we present the Markov variation, a smoothness measure which offers a probabilistic interpretation of graph signal smoothness. This measure is then used to develop an optimization framework for graph signal interpolation. Our…

Signal Processing · Electrical Eng. & Systems 2020-01-29 Ayelet Heimowitz , Yonina C. Eldar

There has been much interest in generalizing Kesten's criterion for amenability in terms of a random walk to other contexts, such as determining amenability of a deck covering group by the bottom of the spectrum of the Laplacian or entropy…

Dynamical Systems · Mathematics 2021-10-06 Rhiannon Dougall

We describe Markov interval maps via branching systems and develop the theory of relative branching systems, characterizing when the associated representations of relative graph C*-algebras are faithful. When the Markov interval maps $f$…

Operator Algebras · Mathematics 2022-06-22 Carlos Correia Ramos , Daniel Gonçalves , Nuno Martins , Paulo R. Pinto

This paper summarizes our latest understanding and results about the application of the Mathematics Of Enumeration to Tanner Graphs that have a regular structure called Balanced Tanner Graphs. Some preliminaries of permutation groups have…

Information Theory · Computer Science 2013-01-01 Vivek S Nittoor , Reiji Suda

This article is concerned with measure equivalence and uniform measure equivalence of locally compact, second countable groups. We show that two unimodular, locally compact, second countable groups are measure equivalent if and only if they…

Group Theory · Mathematics 2019-11-19 Juhani Koivisto , David Kyed , Sven Raum

Fair ranking problems arise in many decision-making processes that often necessitate a trade-off between accuracy and fairness. Many existing studies have proposed correction methods such as adding fairness constraints to a ranking model's…

Machine Learning · Computer Science 2022-04-26 Ryosuke Sonoda

Data sets for fairness relevant tasks can lack examples or be biased according to a specific label in a sensitive attribute. We demonstrate the usefulness of weight based meta-learning approaches in such situations. For models that can be…

Machine Learning · Computer Science 2019-11-12 Dylan Slack , Sorelle Friedler , Emile Givental

Many popular algorithmic fairness measures depend on the joint distribution of predictions, outcomes, and a sensitive feature like race or gender. These measures are sensitive to distribution shift: a predictor which is trained to satisfy…

Machine Learning · Statistics 2022-02-11 Alan Mishler , Niccolò Dalmasso

We define a general notion of a smooth invariant (central) ergodic measure on the space of paths of an $N$-graded graph (Bratteli diagram). It is based on the notion of standardness of the tail filtration in the space of paths, and the…

Representation Theory · Mathematics 2013-12-30 Anatoly Vershik

We consider the flip-width of geometric graphs, a notion of graph width recently introduced by Toru\'nczyk. We prove that many different types of geometric graphs have unbounded flip-width. These include interval graphs, permutation graphs,…

Computational Geometry · Computer Science 2023-06-23 David Eppstein , Rose McCarty

Learning and reasoning over graphs is increasingly done by means of probabilistic models, e.g. exponential random graph models, graph embedding models, and graph neural networks. When graphs are modeling relations between people, however,…

Machine Learning · Computer Science 2021-06-29 Maarten Buyl , Tijl De Bie

A transfunction is a function which maps between sets of finite measures on measurable spaces. Push-forward operators form one important class of examples of transfunctions and are identified with their respective measurable functions. In…

Functional Analysis · Mathematics 2018-04-17 Jason Bentley , Piotr Mikusiński

The definition and implementation of fairness in automated decisions has been extensively studied by the research community. Yet, there hides fallacious reasoning, misleading assertions, and questionable practices at the foundations of the…

Computers and Society · Computer Science 2023-06-05 Robert Lee Poe , Soumia Zohra El Mestari

We consider the problem of producing fair probabilistic classifiers for multi-class classification tasks. We formulate this problem in terms of "projecting" a pre-trained (and potentially unfair) classifier onto the set of models that…

Machine Learning · Computer Science 2022-06-17 Wael Alghamdi , Hsiang Hsu , Haewon Jeong , Hao Wang , P. Winston Michalak , Shahab Asoodeh , Flavio P. Calmon