Timezone: »

Fused sparsity and robust estimation for linear models with unknown variance
Arnak Dalalyan · Yin Chen

Thu Dec 06 02:00 PM -- 12:00 AM (PST) @ Harrah’s Special Events Center 2nd Floor #None

In this paper, we develop a novel approach to the problem of learning sparse representations in the context of fused sparsity and unknown noise level. We propose an algorithm, termed Scaled Fused Dantzig Selector (SFDS), that accomplishes the aforementioned learning task by means of a second-order cone program. A special emphasize is put on the particular instance of fused sparsity corresponding to the learning in presence of outliers. We establish finite sample risk bounds and carry out an experimental evaluation on both synthetic and real data.

Author Information

Arnak Dalalyan (ENSAE - CREST)
Yin Chen (Ecole des Ponts ParisTech)