26 citations · 56 across the 18 of their papers we have counts for
6 papers · 2 filters
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…
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…
Randomness and Permutations in Coordinate Descent Methods
Mert Gurbuzbalaban, Asuman Ozdaglar, Nuri Denizcan Vanli +1
We consider coordinate descent (CD) methods with exact line search on convex quadratic problems. Our main focus is to study the performance of the CD method that use random permuta…
A Newton-CG Algorithm with Complexity Guarantees for Smooth Unconstrained Optimization
Clément W. Royer, Michael O'Neill, Stephen J. Wright
We consider minimization of a smooth nonconvex objective function using an iterative algorithm based on Newton's method and the linear conjugate gradient algorithm, with explicit d…
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…
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…