8 papers
A proximal subgradient method for nonconvex stochastic optimization under the Kurdyka-Łojasiewicz condition
Felipe Atenas, Alejandro Jofré, Pedro Pérez-Aros +1
This work introduces a proximal stochastic subgradient method for minimizing the sum of an expected cost, whose integrand is potentially nonsmooth and nonconvex, and a lower semico…
Sharp bounds for stochastic proximal and projection estimators via radial dominance
Gonzalo Contador, Pedro Pérez-Aros, Emilio Vilches
We study stochastic barycentric estimators for proximal points and metric projections obtained by exponentially reweighting Gaussian perturbations. Our main result is an abstract c…
Differentiability and Approximation of Probability Functions under Gaussian Mixture Models
Gonzalo Contador, Pedro Pérez-Aros, Emilio Vilches
In this work, we study probability functions associated with Gaussian mixture models. Our primary focus is on extending the use of spherical radial decomposition for multivariate G…
Duality for the -convergence of convex functions
Rafael Correa, Pedro Pérez-Aros, José Pablo Santander
We extend the duality principle for the -convergence of convex lower semicontinuous functions, which was previously established only in separable reflexive Banach spaces, to th…
Nonmonotone subgradient methods based on a local descent lemma
Francisco J. Aragón-Artacho, Rubén Campoy, Pedro Pérez-Aros +1
In this paper we present a nonmonotone line search subgradient algorithm tailored to upper- functions. This is a family of nonsmooth and nonconvex functions that sat…
Randomized block proximal method with locally Lipschitz continuous gradient
Pedro Pérez-Aros, Pedro Pérez-Aros, David Torregrosa-Belén +1
Block-coordinate algorithms are recognized to furnish efficient iterative schemes for addressing large-scale problems, especially when the computation of full derivatives entails s…