Adam: A Method for Stochastic Optimization
Work
Year: 2014
Type: preprint
Abstract: We introduce Adam, an algorithm for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimates of lower-order moments. The method is straightforward to impl... more
Source: arXiv (Cornell University)
Authors Diederik P. Kingma, Jimmy Ba
Cites:
Cited by: 51,880
Related to: 10
Citation percentile (by year/subfield): 99.98
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green