linear systems

On Optimal Regularization in Estimation, Detection, and Classification

-

KAUST

In many problems in statistical signal processing, regularization is employed to deal with uncertainty, ill-posedness, and insufficiency of training data. It is possible to tune these regularizers optimally asymptotically, i.e. when the dimension of the problem becomes very large, by using tools from random matrix theory and Gauss Process Theory. In this talk, we demonstrate the optimal turning of regularization for three problems : i) Regularized least squares for solving ill-posed and/or uncertain linear systems, 2) Regularized least squares for signal detection in multiple antenna communication systems and 3) Regularized linear and quadratic discriminant binary classifiers.

Robust fractional-order proportional-integral observer for synchronization of chaotic fractional-order systems

1 min read ·
Ibrahima N' Doye, et al., "Robust fractional-order proportional-integral observer for synchronization of chaotic fractional-order systems", IEEE/CAA Journal of Automatica Sinica 6 (1), 2019, 268. Abstract: In this paper, we propose a robust fractional-order proportional-integral (FOPI) observer for the synchronization of nonlinear fractional-order chaotic systems. The convergence of the observer is proved, and sufficient conditions are derived in terms of linear matrix inequalities (LMIs) approach by using an indirect Lyapunov method. The proposed FOPI observer is robust against Lipschitz

Professor Tareq Al-Naffouri Talk on On Optimal Regularization in Estimation, Detection, and Classification

1 min read ·
On April 30th 2020, Professor Tareq Al-Naffouri delivered a talk on Optimal Regularization in Estimation, Detection, and Classification. Due to the COVID-19 pandemic, the talk was delivered online via Zoom. To find the abstract of the talk, press here.