Back to Results
First PageMeta Content
Stochastic optimization / Quasi-Newton method / Gradient descent / Stochastic gradient descent / BFGS method / Limited-memory BFGS / Stochastic approximation / Hessian matrix / Perceptron / Numerical analysis / Mathematical optimization / Mathematical analysis


Fast large-scale optimization by unifying stochastic gradient and quasi-Newton methods Jascha Sohl-Dickstein, Ben Poole, Surya Ganguli Stanford University {jascha,benpoole,sganguli}@stanford.edu
Add to Reading List

Document Date: 2014-12-13 10:45:07

Open Document

File Size: 643,52 KB

Share Result on Facebook

City

L. A. / /

Company

SIAM Journal / Neural Information Processing Systems / Artificial Neural Networks / GPU / Intel / /

Currency

pence / SGD / /

/

Facility

Surya Ganguli Stanford University / /

IndustryTerm

metric algorithms / grid search / multilayer convolutional network / online learning / online approximation / similar algorithm / double-rank minimization algorithms / /

Organization

Stanford University / /

Person

Kilian Koepsell / Hillel Gauchman / Ruslan R. Salakhutdinov / Oriol Vinyals / Peter Battaglino / Julien Mairal / Antoine Bordes / Daniel Povey / Geoffrey E. Hinton / Jascha Sohl-Dickstein / John Duchi / Peter B. Battaglino / Xavier Glorot / Pascal Vincent / Jochen Trumpf / James Martens / Alex Krizhevsky / Liu / Alfred O Hero / Will Neveitt / Jorge Nocedal / Doron Blatt / Peter Sunehag / Patrick Gallinari / Ruby C Weng / Michael R. DeWeese / Nicol N Schraudolph / Nitish Srivastava / Xavier Muller / Michael DeWeese / Christopher Hillar / Jorge J Mor / Salah Rifai / Yoshua Bengio / Surya Ganguli / Ben Poole / Herbert Robbins / Yoram Singer / Elad Hazan / Richard H Byrd / Gillian M Chin / Sutton Monro / Ilya Sutskever / Jen Lin / John E Dennis Jr / Nicol Schraudolph / Jin Yu / /

Position

Singer / /

ProgrammingLanguage

MATLAB / Python / /

ProvinceOrState

New Brunswick / /

PublishedMedium

Machine Learning / Journal of Machine Learning Research / The Journal of Machine Learning Research / Physical Review Letters / /

SportsLeague

Stanford University / /

Technology

neural network / AdaGrad algorithm / limited memory BFGS algorithm / similar algorithm / BFGS algorithm / 2 Algorithm The algorithm / SFO algorithm / Machine Learning / double-rank minimization algorithms / variable metric algorithms / /

SocialTag