activity
20152019
most citedA Distributed Quasi-Newton Algorithm for Primal and Dual Regularized Empirical Risk Minimization

1 citations · 1 across the 2 of their papers we have counts for

collaborators

6 papers

cs.LG20191 cited

A Distributed Quasi-Newton Algorithm for Primal and Dual Regularized Empirical Risk Minimization

Ching-pei Lee, Cong Han Lim, Stephen J. Wright

We propose a communication- and computation-efficient distributed optimization algorithm using second-order information for solving empirical risk minimization (ERM) problems with…

math.OC2018

First-order algorithms converge faster than on convex problems

Ching-pei Lee, Stephen J. Wright

It is well known that both gradient descent and stochastic coordinate descent achieve a global convergence rate of in the objective value, when applied to a scheme for min…

math.OC2018

Inexact Variable Metric Stochastic Block-Coordinate Descent for Regularized Optimization

Ching-pei Lee, Stephen J. Wright

Block-coordinate descent (BCD) is a popular framework for large-scale regularized optimization problems with block-separable structure. Existing methods have several limitations. T…

math.OC2018

A Distributed Quasi-Newton Algorithm for Empirical Risk Minimization with Nonsmooth Regularization

Ching-pei Lee, Cong Han Lim, Stephen J. Wright

We propose a communication- and computation-efficient distributed optimization algorithm using second-order information for solving ERM problems with a nonsmooth regularization ter…

math.OC2018

Inexact Successive Quadratic Approximation for Regularized Optimization

Ching-pei Lee, Stephen J. Wright

Successive quadratic approximations, or second-order proximal methods, are useful for minimizing functions that are a sum of a smooth part and a convex, possibly nonsmooth part tha…

cs.LG2015

On the Equivalence of CoCoA+ and DisDCA

Ching-pei Lee

In this document, we show that the algorithm CoCoA+ (Ma et al., ICML, 2015) under the setting used in their experiments, which is also the best setting suggested by the authors tha…