Bandit algorithms are concerned with trading exploration with exploitation where a number of options are available but we can only learn their quality by experimenting with them. ...
Discovering the dependencies among the variables of a domain from examples is an important problem in optimization. Many methods have been proposed for this purpose, but few large...
We study the use of low-density generator matrix (LDGM) codes for lossy compression of the Bernoulli symmetric source. First, we establish rigorous upper bounds on the average dist...
Martin J. Wainwright, Elitza N. Maneva, Emin Marti...
Abstract--In this paper we investigate the opportunistic spectrum access in temporal domain where a secondary user shares a radio channel with a primary user during the OFF period ...
A new family of boosting algorithms, denoted TaylorBoost, is proposed. It supports any combination of loss function and first or second order optimization, and includes classical...
Mohammad Saberian, Hamed Masnadi-Shirazi, Nuno Vas...