activity
20132025
most citedParallelizing Stochastic Gradient Descent for Least Squares Regression: mini-batching, averaging, and model misspecification

87 citations · 862 across the 74 of their papers we have counts for

collaborators
Showing 2013Show all

5 papers · 1 filter

cs.DS2013

Path Finding II : An Õ(m sqrt(n)) Algorithm for the Minimum Cost Flow Problem

Yin Tat Lee, Aaron Sidford

In this paper we present an time algorithm for solving the maximum flow problem on directed graphs with edges, vertices, and capacity rat…

cs.DS2013★ 12 cited

Path Finding I :Solving Linear Programs with Õ(sqrt(rank)) Linear System Solves

Yin Tat Lee, Aaron Sidford

In this paper we present a new algorithm for solving linear programs that requires only iterations to solve a linear program with constraints, …

cs.DS2013

Efficient Accelerated Coordinate Descent Methods and Faster Algorithms for Solving Linear Systems

Yin Tat Lee, Aaron Sidford

In this paper we show how to accelerate randomized coordinate descent methods and achieve faster convergence rates without paying per-iteration costs in asymptotic running time. In…

cs.DS2013★ 7 cited

An Almost-Linear-Time Algorithm for Approximate Max Flow in Undirected Graphs, and its Multicommodity Generalizations

Jonathan A. Kelner, Yin Tat Lee, Lorenzo Orecchia +1

In this paper, we introduce a new framework for approximately solving flow problems in capacitated, undirected graphs and apply it to provide asymptotically faster algorithms for t…

cs.DS2013

A Simple, Combinatorial Algorithm for Solving SDD Systems in Nearly-Linear Time

Jonathan A. Kelner, Lorenzo Orecchia, Aaron Sidford +1

In this paper, we present a simple combinatorial algorithm that solves symmetric diagonally dominant (SDD) linear systems in nearly-linear time. It uses very little of the machiner…