Optimization on a Budget: A Reinforcement Learning Approach

Many popular optimization algorithms, like the Levenberg-Marquardt algorithm (LMA), use heuristic-based "controllers" that modulate the behavior of the optimizer during the optimization process. For example, in the LMA a damping parameter is dynamically modified based on a set of rules that were developed using heuristic arguments. Reinforcement learning (RL) is a machine learning approach to learn optimal controllers from examples and thus is an obvious candidate to improve the heuristic-based controllers implicit in the most popular and heavily used optimization algorithms. Improving the performance of off-the-shelf optimizers is particularly important for time-constrained optimization problems. For example the LMA algorithm has become popular for many real-time computer vision problems, including object tracking from video, where only a small amount of time can be allocated to the optimizer on each incoming video frame. Here we show that a popular modern reinforcement le...

• Type: Conference
• Year: 2008
• Where: NIPS
• Authors: Paul Ruvolo, Ian R. Fasel, Javier R. Movellan
• Keywords: Information Technology, LMA Algorithm, NIPS 2008, Optimization Algorithms, Standard Lma