Nuclear Atomic Norm for parametric estimation of sparse channels

Parametric channel estimation in mmWave not only enables the anticipated large spectral efficiency gains of \acs{MIMO} systems but also reveals important propagation parameters, allowing for a low complexity representation of the channel matrix. In this work, we propose to use atomic norm as a gridless multidimensional spectral estimation approach to address parametric channel estimation where both AoD and AoA are identified. The conditions for recovery of the propagation parameters are given depending on properties of the measurement matrix, and on structural features such as the antenna geometry or the number of scatters to resolve. The proposed methodology is compared against several state-of-the-art parametric approaches.

Rényi Entropy Bounds on the Active Learning Cost-Performance Tradeoff

Semi-supervised classification, one of the most prominent fields in machine learning, studies how to combine the statistical knowledge of the often abundant unlabeled data with the often limited labeled data in order to maximize overall classification accuracy. In this context, the process of actively choosing the data to be labeled is referred to as active learning. In this paper, we initiate the non-asymptotic analysis of the optimal policy for semi-supervised classification with actively obtained labeled data. Considering a general Bayesian classification model, we provide the first characterization of the jointly optimal active learning and semi-supervised classification policy, in terms of the cost-performance tradeoff driven by the label query budget (number of data items to be labeled) and overall classification accuracy. Leveraging recent results on the R\'enyi Entropy, we derive tight information-theoretic bounds on such active learning cost-performance tradeoff.