Learning to learn by gradient descent by gradient descent
Neural and Evolutionary Computing
2016-12-01 v2 Machine Learning
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.
Cite
@article{arxiv.1606.04474,
title = {Learning to learn by gradient descent by gradient descent},
author = {Marcin Andrychowicz and Misha Denil and Sergio Gomez and Matthew W. Hoffman and David Pfau and Tom Schaul and Brendan Shillingford and Nando de Freitas},
journal= {arXiv preprint arXiv:1606.04474},
year = {2016}
}