Making algorithms fair - Hallo friendsNOT SOME IMPORTANT INFORMATION, In the article you read this time with the title Making algorithms fair, We have prepared this article for you to read and retrieve information therein. Hopefully the contents of postings Article capital markets, Article economy, Article health, Article News, Article politics, Article sports, We write this you can understand. Alright, good read.

Title : Making algorithms fair
link : Making algorithms fair

Making algorithms fair

Fairness is elusive, even in algorithms. "Color blindness" doesn't do the trick, since minority populations may differ in other ways from majority populations.
My attention was drawn to this news story  about ongoing work by U. Penn computer scientists: Combatting ‘Fairness Gerrymandering’ with Socially Conscious Algorithms

And here's the article on which the story is based:

Preventing Fairness Gerrymandering: Auditing and Learning for Subgroup Fairness

Michael Kearns, Seth Neel, Aaron Roth, Zhiwei Steven Wu

(Submitted on 14 Nov 2017 (v1), last revised 8 Jan 2018 (this version, v3))

The most prevalent notions of fairness in machine learning are statistical definitions: they fix a small collection of pre-defined groups, and then ask for parity of some statistic of the classifier across these groups. Constraints of this form are susceptible to intentional or inadvertent "fairness gerrymandering", in which a classifier appears to be fair on each individual group, but badly violates the fairness constraint on one or more structured subgroups defined over the protected attributes. We propose instead to demand statistical notions of fairness across exponentially (or infinitely) many subgroups, defined by a structured class of functions over the protected attributes. This interpolates between statistical definitions of fairness and recently proposed individual notions of fairness, but raises several computational challenges. It is no longer clear how to audit a fixed classifier to see if it satisfies such a strong definition of fairness. We prove that the computational problem of auditing subgroup fairness for both equality of false positive rates and statistical parity is equivalent to the problem of weak agnostic learning, which means it is computationally hard in the worst case, even for simple structured subclasses.
We then derive two algorithms that provably converge to the best fair classifier, given access to oracles which can solve the agnostic learning problem. The algorithms are based on a formulation of subgroup fairness as a two-player zero-sum game between a Learner and an Auditor. Our first algorithm provably converges in a polynomial number of steps. Our second algorithm enjoys only provably asymptotic convergence, but has the merit of simplicity and faster per-step computation. We implement the simpler algorithm using linear regression as a heuristic oracle, and show that we can effectively both audit and learn fair classifiers on real datasets.

Thus Article Making algorithms fair

That's an article Making algorithms fair This time, hopefully can give benefits to all of you. well, see you in posting other articles.

You are now reading the article Making algorithms fair with the link address https://notsomeimportant.blogspot.com/2018/02/making-algorithms-fair.html

Tweet

Subscribe to receive free email updates: