Despite the impressive numerical performance of quasi-Newton and
Anderso...
We propose SING (StabIlized and Normalized Gradient), a plug-and-play
te...
Computing the Jacobian of the solution of an optimization problem is a
c...
The recently developed average-case analysis of optimization methods all...
We consider the problem of upper bounding the expected log-likelihood
su...
This paper considers classification problems with hierarchically organiz...
This monograph covers some recent advances on a range of acceleration
te...
Quasi-Newton techniques approximate the Newton step by estimating the He...
Advances in generative modeling and adversarial learning have given rise...
We develop a framework for designing optimal quadratic optimization meth...
We use matrix iteration theory to characterize acceleration in smooth ga...
Data-driven model training is increasingly relying on finding Nash equil...
The Regularized Nonlinear Acceleration (RNA) algorithm is an acceleratio...
Regularized nonlinear acceleration (RNA) is a generic extrapolation sche...