Hacker News Reader

Comment by Hendrikto | Hacker News Reader

Unequal outcome != bias. Most SJWs don‘t seem to understand this. Of course it can be an indicator that there may be bias, but it is FAR from a proof thereof.

I can easily write you a completely unbiased “model” predicting who comitted crimes:

    func probability_of_comitting_crime():
        return 1/human_population

This is 100% unbiased and treats everybody the same. It’s also 100% useless...

View on HN

The problem is that people view pure statistical based crime probability as "unbiased" because... math. It's not! Most bias is deeply hidden, and our training data comes directly or indirectly from some form of human subjectivity.

The more autonomy plays a role in our lives, the more aware we need to be of how internal bias from human source has affected things like predictions.

And please, there is nothing more flippant and off-putting than railing against "SJWs," this is a topic that demands thoughtfulness.

I still see people call policing maps "crime maps" as though you could map out all the crime like in SimCity.

> The problem is that people view pure statistical based crime probability as "unbiased" because... math. It's not!

Can you explain what you mean? “Biased” usually means not using just statistics but also extra-statistical personal convictions. What does “unbiased” mean for you?

Where do the numbers come from? What is the context of collection of data? What is the context of the classification of training data?

There are hundreds of questions like that which apply. It's not (necessarily, it certainly can be) the algorithm that carries bias, it's the data.

> Unequal outcome != bias.

Sure, which is why the fair machine learning literature has developed more nuanced (and IMO better) definitions of fair predictors.

For example, suppose you have some sensitive attribute A (say race) and want to know some outcome Y. A predictor \hat Y satisfies equalized odds if \hat Y and A are conditionally independent given Y. In binary classification, this means that the classifier has identical false positive rates and false negative rates across races. So e.g. your false negative rate for white people must be the same as your false negative rate for black people. Note that a perfectly accurate classifier satisfies equalized odds -- roughly, its a way of guaranteeing that errors are not concentrated in some group.

I think it's unfair to characterize fair ML research as the work of "SJWs". There's a lot of smart, technical work done by smart, technical people thinking hard about these problems.

Moritz Hardt's course on the topic is still a decent intro: https://fairmlclass.github.io/

Oh that’s interesting! So you can have your “creditworthiness AI” \hat Y) predict that disproportionately more black (A) people are not creditworthy, as long as that’s (roughly) in line with the actual creditworthiness (Y) as determined by the “supervisor”.

That's also a good point -- evaluating fairness against labelled data breaks down if the labels themselves are biased in some way. IMO (and I am not familiar with the entire fair ML literature), we still lack technical tools to address biased data well.

I didn’t mean that they’re biased, just that being “black” correlates with “being poor”, which is not biased in any way but might still appear so based on superficial view(well, the data/AI isn’t biased, though the society might be but that’s not the bank’s problem...)

Edit: biased not busy.

That correlation is a "bias", or maybe better an "unfairness".

Such a system would end up requiring black people have higher credit scores than otherwise equal white counterparts, in order to be granted whatever thing it is. That's, as modern feminist/race theory might define it, an implicit bias. Nowhere is anyone explicitly stating "black implies bad", but the way the model is built creates unequal representation.

No no, what I mean, and is AFAIK visible in the data, is that the poor/low credit people are disproportionately black. So even if the AI/statistics ignore race (as they should), the result will be that blacks have lower credit scores (on average, because they poorer).

I don't think we're disagreeing.

That part is to be expected, the important thing is that you don't then recorrelate, either explicity or implicitly, race with the lower credit scores, that can essentially double count race (via income and then via the second check) and that's what you want to avoid.

Ok yeah then we agree. You definitely shouldn’t feed “irrelevant” features to the AI (i.e. those you don’t want it to discriminate/regress upon) otherwise it will overfit, in the best case to the noise, in the worst to the bias.

Reply on news.ycombinator.com