AdaGrad: Difference between revisions
No edit summary |
(→Theory) |
||
| Line 12: | Line 12: | ||
== Applications == | == Applications == | ||
== Empirical Performance == | === Empirical Performance === | ||
== Summary and Discussion == | == Summary and Discussion == | ||
== References == | == References == | ||
Revision as of 14:02, 26 November 2021
Author: Daniel Villarraga (SYSEN 6800 Fall 2021)
Introduction
AdaGrad is a family of sub-gradient algorithms for stochastic optimization. The algorithms belonging to that family are similar to second-order stochastic gradient descend with an approximation for the Hessian of the optimized function. Intuitively, it adapts the learning rate for each feature depending on the estimated geometry of the function; additionally, it tends to assign higher learning rates to infrequent features, which ensures that the updates are significant each time (independent of feature frequency).
AdaGrad was introduced by Duchi et al.[1] in a highly cited paper published in the Journal of machine learning research in 2011. It is arguably one of the most popular algorithms for machine learning, and it influenced the development of the Adam algorithm[2].