activity
20132020
most citedRandomized projection methods for convex feasibility problems: conditioning and convergence rates

11 citations · 26 across the 6 of their papers we have counts for

collaborators

9 papers

cs.LG2020

Stochastic Proximal Gradient Algorithm with Minibatches. Application to Large Scale Learning Models

Andrei Patrascu, Ciprian Paduraru, Paul Irofti

Stochastic optimization lies at the core of most statistical learning models. The recent great development of stochastic algorithmic tools focused significantly onto proximal gradi…

math.OC2019

Stochastic proximal splitting algorithm for composite minimization

Andrei Patrascu, Paul Irofti

Supported by the recent contributions in multiple branches, the first-order splitting algorithms became central for structured nonsmooth optimization. In the large-scale or noisy c…

math.OC2019

New nonasymptotic convergence rates of stochastic proximal pointalgorithm for convex optimization problems

Andrei Patrascu

Large sectors of the recent optimization literature focused in the last decade on the development of optimal stochastic first order schemes for constrained convex models under prog…

math.OC201811 cited

Randomized projection methods for convex feasibility problems: conditioning and convergence rates

Ion Necoara, Peter Richtarik, Andrei Patrascu

Finding a point in the intersection of a collection of closed convex sets, that is the convex feasibility problem, represents the main modeling strategy for many computational prob…

math.OC20179 cited

Nonasymptotic convergence of stochastic proximal point algorithms for constrained convex optimization

Andrei Patrascu, Ion Necoara

A very popular approach for solving stochastic optimization problems is the stochastic gradient descent method (SGD). Although the SGD iteration is computationally cheap and the pr…

math.OC2015

Complexity certifications of first order inexact Lagrangian methods for general convex programming

Ion Necoara, Andrei Patrascu, Angelia Nedić

In this chapter we derive computational complexity certifications of first order inexact dual methods for solving general smooth constrained convex problems which can arise in real…