Glossary¶
- Adam¶
A SGD-based optimization algorithm. See [GLO-KB15] for details.
- ADMM¶
The alternating direction method of multipliers (ADMM) algorithm. See [GLO-BPC+11] for details.
- BFGS¶
The Broyden-Fletcher-Goldfarb-Shanno (BFGS) algorithm.
- IIS¶
The improved iterative scaling (IIS) algorithm.
- MaxEnt¶
The maximum entropy (MaxEnt) model.
- RProp¶
The resilient backpropagation (RProp) algorithm. See [GLO-RB93] for details.
References¶
Diederik P. Kingma and Jimmy Lei Ba. Adam: a method for stochastic optimization. In Proceedings of the International Conference on Learning Representations. 2015.
Stephen Boyd, Neal Parikh, Eric Chu, Borja Peleato, Jonathan Eckstein, and others. Distributed optimization and statistical learning via the alternating direction method of multipliers. Foundations and Trends® in Machine learning, 3(1):1–122, 2011. URL: https://doi.org/10.1561/2200000016.
Martin Riedmiller and Heinrich Braun. A direct adaptive method for faster backpropagation learning: the RPROP algorithm. In Proceedings of International Conference on Neural Networks, 586–591. 1993. URL: https://doi.org/10.1109/ICNN.1993.298623.