On the impossibility of non-trivial accuracy under fairness constraints

by   Carlos Pinzón, et al.

One of the main concerns about fairness in machine learning (ML) is that, in order to achieve it, one may have to renounce to some accuracy. Having this trade-off in mind, Hardt et al. have proposed the notion of equal opportunities (EO), designed so as to be compatible with accuracy. In fact, it can be shown that if the source of input data is deterministic, the two notions go well along with each other. In the probabilistic case, however, things change. As we show, there are probabilistic data sources for which EO can only be achieved at the total detriment of accuracy, i.e. among the models that achieve EO, those whose prediction does not depend on the input have the highest accuracy.


page 1

page 2

page 3

page 4


The Sharpe predictor for fairness in machine learning

In machine learning (ML) applications, unfair predictions may discrimina...

Survey on Fairness Notions and Related Tensions

Automated decision systems are increasingly used to take consequential d...

An Empirical Study of Rich Subgroup Fairness for Machine Learning

Kearns et al. [2018] recently proposed a notion of rich subgroup fairnes...

Fairness and efficiency for probabilistic allocations with endowments

We propose a notion of fairness for allocation problems in which differe...

Fairness in Influence Maximization through Randomization

The influence maximization paradigm has been used by researchers in vari...

Please sign up or login with your details

Forgot password? Click here to reset