2016 LearningtoLearnbyGradientDescen

• (Andrychowicz et al., 2016) ⇒ Marcin Andrychowicz, Misha Denil, Sergio Gómez Colmenarejo, Matthew W. Hoffman, David Pfau, Tom Schaul, Brendan Shillingford, and Nando de Freitas. (2016). “Learning to Learn by Gradient Descent by Gradient Descent.” In: Proceedings of the 30th International Conference on Neural Information Processing Systems. ISBN:978-1-5108-3881-9

Subject Headings: Automated Supervised ML.

Cited By

• http://scholar.google.com/scholar?q=%222016%22+Learning+to+Learn+by+Gradient+Descent+by+Gradient+Descent
• http://dl.acm.org/citation.cfm?id=3157382.3157543&preflayout=flat#citedby

Quotes

Abstract

The move from hand-designed features to learned features in machine learning has been wildly successful. In spite of this, optimization algorithms are still designed by hand. In this paper we show how the design of an optimization algorithm can be cast as a learning problem, allowing the algorithm to learn to exploit structure in the problems of interest in an automatic way. Our learned algorithms, implemented by LSTMs, outperform generic, hand-designed competitors on the tasks for which they are trained, and also generalize well to new tasks with similar structure. We demonstrate this on a number of tasks, including simple convex problems, training neural networks, and styling images with neural art.

References

;

	Author	volume	Date Value	title	type	journal	titleUrl	doi	note	year
2016 LearningtoLearnbyGradientDescen	Misha Denil Nando de Freitas Sergio Gómez Colmenarejo Marcin Andrychowicz Matthew W. Hoffman David Pfau Tom Schaul Brendan Shillingford			Learning to Learn by Gradient Descent by Gradient Descent						2016