221 citations · 257 across the 3 of their papers we have counts for
3 papers
A General Framework for Structured Sparsity via Proximal Optimization
Andreas Argyriou, Luca Baldassarre, Jean Morales +1
We study a generalized framework for structured sparsity. It extends the well-known methods of Lasso and Group Lasso by incorporating additional constraints on the variables as par…
Efficient First Order Methods for Linear Composite Regularizers
Andreas Argyriou, Charles A. Micchelli, Massimiliano Pontil +2
A wide class of regularization problems in machine learning and statistics employ a regularization term which is obtained by composing a simple convex function ωwith a linear trans…
Empirical Bernstein Bounds and Sample Variance Penalization
Andreas Maurer, Massimiliano Pontil
We give improved constants for data dependent and variance sensitive confidence bounds, called empirical Bernstein bounds, and extend these inequalities to hold uniformly over clas…