Certifying and removing disparate impact · HackerPapers discussions

Certifying and removing disparate impact — mentioned by Smerity

Tue, 19 Jul 2016 07:14:56 GMT

The European Union are likely to accelerate much of this type of research. They recently introduced regulations specifically targeting algorithmic decision-making and a "right to explanation" for automated decisions. There's a Wired article[1] on the general scene and a paper that investigates the impact it may have on the industry[2]. Regarding differential discrimination, check out these two papers[3][4] - they're very similar to your idea :) [1]: http://www.wired.com/2016/07/artificial-intelligence-setting... [2]: http://arxiv.org/abs/1606.08813v2 [3]: http://arxiv.org/abs/1511.05897 [4]…

Paper and discussion history. A mention is not an endorsement.

Certifying and removing disparate impact — mentioned by Smerity

Tue, 19 Jul 2016 06:44:45 GMT

The issue is not whether justice can be codified. Let us assume that you can and it's outlined on page 3 of your document. Providing examples to an ML model don't guarantee it will codify anything similar to that. This is a fundamental issue. Most machine learning models aren't highly interpretable and can also act in unexpected ways. Re: (a) variables with a low correlation to race / (b) dishonest about how much ML systems can "infer hidden variables": (b) The example you point to is specifically adversarial modification to the input data. I'm not sure how that's relevant to your point at…

Paper and discussion history. A mention is not an endorsement.

Certifying and removing disparate impact — mentioned by mizzao

Thu, 24 Mar 2016 21:44:17 GMT

Sendhil Mullainathan (econ prof at Harvard) is doing some work on using machine learning to predict whether people should be granted bail. The machine discrimination (no pun intended) issues here could be quite terrifying. Not published yet, but example abstract: http://inequality.hks.harvard.edu/event/sendhil-mullainathan... On the other hand, there's starting to be some research on how to codify and prevent this in ML. For example: http://arxiv.org/abs/1412.3756

Paper and discussion history. A mention is not an endorsement.

Certifying and removing disparate impact — mentioned by Malician

Sun, 27 Sep 2015 22:08:03 GMT

Sure, and I agree. But that's not what they're doing here. Paper is available online: http://arxiv.org/pdf/1412.3756v3.pdf

Paper and discussion history. A mention is not an endorsement.