DMCA
TUNING-FREE STEP-SIZE ADAPTATION
Cached
Download Links
BibTeX
@MISC{Rupam_tuning-freestep-size,
author = {Ashique Rupam and Mahmood Richard and S. Sutton and Thomas Degris and Patrick M. Pilarski},
title = {TUNING-FREE STEP-SIZE ADAPTATION},
year = {}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
Incremental learning algorithms based on gradient descent are effective and popular in online supervised learning, reinforcement learning, signal processing, and many other application areas. An oft-noted drawback of these algorithms is that they include a step-size parameter that needs to be tuned for best performance, which may require manual intervention and significant domain knowledge or additional data. In many cases, an entire vector of step-size parameters (e.g., one for each input feature) needs to be tuned in order to attain the best performance of the algorithm. To address this, several methods have been proposed for adapting step sizes online. For example, Sutton’s IDBD method can find the best vector step size for the LMS algorithm, and Schraudolph’s ELK1 method, an extension of IDBD to neural networks, has proven effective
Keyphrases
tuning-free step-size adaptation step-size parameter significant domain knowledge gradient descent input feature vector step size idbd method elk1 method manual intervention oft-noted drawback neural network lm algorithm several method entire vector many case signal processing many application area additional data reinforcement learning step size online
