The seminal work of "equalized coverage" proposed an uncertainty-aware fairness notion.

We consider both exact andapproximate recoveryofthelabels. Our results hold for anyconstant-factor approximation tothek-means problem.

Code generation models have increasingly become integral to aiding software development.

Whileminimax optimal algorithms exist for this problem, its instance-dependent complexity remains elusiveinepisodic Markovdecision processes (MDPs).

Our second estimator perturbs the empirical mean of the data set with noise calibrated to the empirical covariance,withoutreleasing thecovariance itself.

Unfortunately, in high dimensions, releasing the empirical mean leads to concrete privacy breaches [32, 41].

Weconsider the task of learning an RBM given samples generated according to it.