In a partial monitoring game, the learner repeatedly chooses an action, the environment responds with an outcome, and then the learner suffers a loss and receives a feedback signal, both of which are fixed functions of the action and the outcome. The goal of the learner is to minimize his regret, which is the difference between his total cumulative loss and the total loss of the best fixed acti...

This paper studies the issue of optimal deconvolution density estimation using wavelets. We explore the asymptotic properties of estimators based on thresholding of estimated wavelet coe cients. Minimax rates of convergence under the integrated square loss are studied over Besov classes B pq of functions for both ordinary smooth and supersmooth convolution kernels. The minimax rates of converge...

On-grid based direction-of-arrival (DOA) estimation methods rely on the resolution of a difficult group-sparse optimization problem that involves $\ell _{2,0}$ pseudo-norm. In this work, we show an exact relaxation can be obtained by replacing term with group minimax concave penalty suitable parameters. This is more amenable to non-convex algorithms as it continuous and admits less local (not g...