Skip to yearly menu bar Skip to main content


Learning to learn by gradient descent by gradient descent

Marcin Andrychowicz · Misha Denil · Sergio Gómez · Matthew Hoffman · David Pfau · Tom Schaul · Nando de Freitas

Area 5+6+7+8 #9

Keywords: [ Deep Learning or Neural Networks ]


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.

Live content is unavailable. Log in and register to view live content