Timezone: »

Can You Learn an Algorithm? Generalizing from Easy to Hard Problems with Recurrent Networks
Avi Schwarzschild · Eitan Borgnia · Arjun Gupta · Furong Huang · Uzi Vishkin · Micah Goldblum · Tom Goldstein

Fri Dec 10 08:30 AM -- 10:00 AM (PST) @ None #None

Deep neural networks are powerful machines for visual pattern recognition, but reasoning tasks that are easy for humans may still be difficult for neural models. Humans possess the ability to extrapolate reasoning strategies learned on simple problems to solve harder examples, often by thinking for longer. For example, a person who has learned to solve small mazes can easily extend the very same search techniques to solve much larger mazes by spending more time. In computers, this behavior is often achieved through the use of algorithms, which scale to arbitrarily hard problem instances at the cost of more computation. In contrast, the sequential computing budget of feed-forward neural networks is limited by their depth, and networks trained on simple problems have no way of extending their reasoning to accommodate harder problems. In this work, we show that recurrent networks trained to solve simple problems with few recurrent steps can indeed solve much more complex problems simply by performing additional recurrences during inference. We demonstrate this algorithmic behavior of recurrent networks on prefix sum computation, mazes, and chess. In all three domains, networks trained on simple problem instances are able to extend their reasoning abilities at test time simply by "thinking for longer."

Author Information

Avi Schwarzschild (University of Maryland)
Eitan Borgnia (University of Maryland)
Arjun Gupta (University of Maryland, College Park)
Furong Huang (University of Maryland)

Furong Huang is an assistant professor of computer science. Huang’s research focuses on machine learning, high-dimensional statistics and distributed algorithms—both the theoretical analysis and practical implementation of parallel spectral methods for latent variable graphical models. Some applications of her research include developing fast detection algorithms to discover hidden and overlapping user communities in social networks, learning convolutional sparse coding models for understanding semantic meanings of sentences and object recognition in images, healthcare analytics by learning a hierarchy on human diseases for guiding doctors to identify potential diseases afflicting patients, and more. Huang recently completed a postdoctoral position at Microsoft Research in New York.

Uzi Vishkin (University of Maryland, College Park)
Micah Goldblum (University of Maryland)
Tom Goldstein (Rice University)

More from the Same Authors