40 citations · 46 across the 14 of their papers we have counts for
5 papers · 1 filter
GeNIOS: an (almost) second-order operator-splitting solver for large-scale convex optimization
Theo Diamandis, Zachary Frangella, Shipu Zhao +2
We introduce the GEneralized Newton Inexact Operator Splitting solver (GeNIOS) for large-scale convex optimization. GeNIOS speeds up ADMM by approximately solving approximate subpr…
PROMISE: Preconditioned Stochastic Optimization Methods by Incorporating Scalable Curvature Estimates
Zachary Frangella, Pratik Rathore, Shipu Zhao +1
This paper introduces PROMISE (econditioned Stochastic ptimization ethods by ncorporating calable Curvature $\textbf{E}…
On the (linear) convergence of Generalized Newton Inexact ADMM
Zachary Frangella, Theo Diamandis, Bartolomeo Stellato +1
This paper presents GeNI-ADMM, a framework for large-scale composite convex optimization that facilitates theoretical analysis of both existing and new approximate ADMM schemes. Ge…
SketchySGD: Reliable Stochastic Optimization via Randomized Curvature Estimates
Zachary Frangella, Pratik Rathore, Shipu Zhao +1
SketchySGD improves upon existing stochastic gradient methods in machine learning by using randomized low-rank approximations to the subsampled Hessian and by introducing an automa…
NysADMM: faster composite convex optimization via low-rank approximation
Shipu Zhao, Zachary Frangella, Madeleine Udell
This paper develops a scalable new algorithm, called NysADMM, to minimize a smooth convex loss function with a convex regularizer. NysADMM accelerates the inexact Alternating Direc…