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 algorit...

Nesterov’s accelerated gradient method for minimizing a smooth strongly convex function f is known to reduce f(xk) − f(x∗) by a factor of ∈ (0, 1) after k ≥ O( √ L/` log(1/ )) iterations, where `, L are the two parameters of smooth strong convexity. Furthermore, it is known that this is the best possible complexity in the function-gradient oracle model of computation. The method of linear conju...

Image segmentation is currently a prominent topic for both military and commercial researchers. This paper concentrates on the image segmentation based on the combination of modulated intensity gradient and texture gradient. Image segmentation is an integral part of image analysis. In image processing different processes are done on images to enhance it at different parameters. These processes ...

Abstract Despite their many empirical successes, approximate value-function based approaches to reinforcement learning suffer from a paucity of theoretical guarantees on the performance of the policy generated by the value-function. In this paper we pursue an alternative approach: first compute the gradient of the average reward with respect to the parameters controlling the state transitions i...