Towards fair machine learning using combinatorial methods

With the rise of artificial intelligence and machine learning in the last decade, there has been an increasing interest in developing a solid theory and implementing algorithmic fairness, which has eventually resulted in a large volume of work over the past few years. Despite the enormous amount of...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Evolutionary intelligence Ročník 16; číslo 3; s. 903 - 916
Hlavní autoři: Saraswat, Anant, Pal, Manjish, Pokhriyal, Subham, Abhishek, Kumar
Médium: Journal Article
Jazyk:angličtina
Vydáno: Berlin/Heidelberg Springer Berlin Heidelberg 01.06.2023
Springer Nature B.V
Témata:
Applications of Mathematics
Artificial Intelligence
Bias
Bioinformatics
Classification
Combinatorial analysis
Control
Decision making
Engineering
Genetic algorithms
Linear programming
Machine learning
Mathematical and Computational Engineering
Mechatronics
Optimization techniques
Pareto optimum
Research Paper
Robotics
Software
Statistical Physics and Dynamical Systems
Combinatorics
Fair Machine Learning
Discrepancy Theory
Linear Programming
ISSN:1864-5909, 1864-5917
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:With the rise of artificial intelligence and machine learning in the last decade, there has been an increasing interest in developing a solid theory and implementing algorithmic fairness, which has eventually resulted in a large volume of work over the past few years. Despite the enormous amount of work done on the topic over a concise period, there has been little consensus of a unifying theory of algorithmic fairness. In this paper, we develop a notion of fairness that is based on the notion of discrepancy of set systems, a widely studied topic in the theory of computer science and combinatorics. (Chazelle Bernard in The discrepancy method: randomness and complexity. Cambridge University Press (2001)).
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1864-5909
1864-5917
DOI:10.1007/s12065-022-00702-5