An Efficient Projection for L1 Infinity Regularization
published: Aug. 26, 2009, recorded: June 2009, views: 1031
Report a problem or upload filesIf 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.
In recent years the L1,Infinity norm has been proposed for joint regularization. In essence, this type of regularization aims at extending the L1 framework for learning sparse models to a setting where the goal is to learn a set of jointly sparse models. In this paper we derive a simple and effective projected gradient method for optimization of L1,Infinity regularized problems. The main challenge in developing such a method resides on being able to compute efficient projections to the L1,Infinity ball. We present an algorithm that works in O(n log n) time and O(n) memory where n is the number of parameters. We test our algorithm in a multi-task image annotation problem. Our results show that L1,Infinity leads to better performance than both L2 and L1 regularization and that it is is effective in discovering jointly sparse solutions.
Link this pageWould you like to put a link to this lecture on your homepage?
Go ahead! Copy the HTML snippet !