Skip to main navigation
Skip to search
Skip to main content
Princeton University Home
Help & FAQ
Home
Profiles
Research units
Facilities
Projects
Research output
Press/Media
Search by expertise, name or affiliation
Exponentiated Gradient vs. Meets Gradient Descent
Udaya Ghai
,
Elad Hazan
, Yoram Singer
Computer Science
Center for Statistics & Machine Learning
Princeton Language and Intelligence (PLI)
Research output
:
Contribution to journal
›
Conference article
›
peer-review
26
Scopus citations
Overview
Fingerprint
Fingerprint
Dive into the research topics of 'Exponentiated Gradient vs. Meets Gradient Descent'. Together they form a unique fingerprint.
Sort by
Weight
Alphabetically
Keyphrases
Gradient Descent
100%
Exponentiated Gradient
100%
Multiplicative Updates
100%
Rectangular Matrices
66%
Machine Learning
33%
Popular
33%
Tight
33%
Gradient Method
33%
Matrix-based
33%
Update Mechanism
33%
Regret Bounds
33%
Positive Definite Matrix
33%
Stochastic Gradient Descent
33%
One-class Learning
33%
Entropy Function
33%
Multiplicative Methods
33%
Negative numbers
33%
Mathematics
Matrix (Mathematics)
100%
Multiplicative
100%
Regularization
50%
Stochastics
25%
Positive Semidefinite Matrix
25%
Negative Number
25%