Differential privacy is the de facto standard for protecting privacy in ...
Classical wisdom suggests that estimators should avoid fitting noise to
...
Popular iterative algorithms such as boosting methods and coordinate des...
Good generalization performance on high-dimensional data crucially hinge...
We provide matching upper and lower bounds of order σ^2/log(d/n) for
the...
Numerous recent works show that overparameterization implicitly reduces
...
Kernel ridge regression is well-known to achieve minimax optimal rates i...
Dilated Convolutions have been shown to be highly useful for the task of...