Rapid Stochastic Gradient Descent: Accelerating Machine Learning
published: Feb. 25, 2007, recorded: February 2006, views: 10075
Slides
Related content
Report a problem or upload files
If you have found a problem with this lecture or would like to send us extra material, articles, exercises, etc., please use our ticket system to describe your request and upload the data.Enter your e-mail into the 'Cc' field, and we will keep you updated with your request's status.
Description
The incorporation of online learning capabilities into real-time computing systems has been hampered by a lack of efficient, scalable optimization algorithms for this purpose: second-order methods are too expensive for large, nonlinear models, conjugate gradient does not tolerate the noise inherent in online learning, and simple gradient descent, evolutionary algorithms, etc., are unacceptably slow to converge. I am addressing this problem by developing new ways to accelerate stochastic gradient descent, using second-order gradient information obtained through the efficient computation of curvature matrix-vector products. In the stochastic meta-descent (SMD) algorithm, this cheap curvature information is built up iteratively into a stochastic approximation of Levenberg-Marquardt second-order gradient steps, which are then used to adapt individual gradient step sizes. SMD handles noisy, correlated, non-stationary signals well, and approaches the rapid convergence of second-order methods at only linear cost per iteration, thus scaling up to extremely large nonlinear systems. To date it has enabled new adaptive techniques in computational fluid dynamics and computer vision. Our most recent development is a version of SMD operating in reproducing kernel Hilbert space.
Link this page
Would you like to put a link to this lecture on your homepage?Go ahead! Copy the HTML snippet !
Reviews and comments:
Very good explanation of the SMD algorithm by the inventor himself. Keep up the good work!.
Extremely superb lecture! Started from the basics and explained very cogently.
Write your own review or comment: