This paper reviews recent advances on online/adaptive sparsity-promoting algorithms. The emphasis is on on a recent family of schemes, which build upon convex analytic tools. The benefits of this algorithmic family is that it can easily deal with the existence of a set of convex constraints and also to bypass the need of differentiability of cost functions. It can thus deal well with notions related to robustness and their associated costs. Extensions to constraints, which are realized via mappings whose fixed point set are non-convex, are also discussed. The case of learning in a distributed fashion is also discussed.
|Original language||English (US)|
|Title of host publication||11th IFAC International Workshop on Adaptation and Learning in Control and Signal Processing, ALCOSP 2013 - Proceedings|
|Number of pages||9|
|State||Published - 2013|
|Event||11th IFAC International Workshop on Adaptation and Learning in Control and Signal Processing, ALCOSP 2013 - Caen, France|
Duration: Jul 3 2013 → Jul 5 2013
|Name||IFAC Proceedings Volumes (IFAC-PapersOnline)|
|Other||11th IFAC International Workshop on Adaptation and Learning in Control and Signal Processing, ALCOSP 2013|
|Period||7/3/13 → 7/5/13|
Bibliographical noteFunding Information:
⋆ This work was partially Supported by the NSRF - ARISTEIA programme for Education and Lifelong Learning, “ASSURANCE’, co-funded by the EU and the Greek State and the Marie Curie, FP7-PEOPLE-2011-IEF fellowship, “SOL”.