Stochastic gradient descent (SGD) uses approximate gradients estimated from subsets of the training data and updates the parameters in an online fashion. This learning framework i...
Consider the following problem: given a metric space, some of whose points are "clients," select a set of at most k facility locations to minimize the average distance f...
Anupam Gupta, Katrina Ligett, Frank McSherry, Aaro...
Several inverse problems exist in the atmospheric sciences that are computationally costly when using traditional gradient based methods. Unfortunately, many standard evolutionary ...
Monte Lunacek, L. Darrell Whitley, Philip Gabriel,...
In this paper we introduce a general strategy for approximating the solution to minimisation problems in random regular graphs. We describe how the approach can be applied to the m...
We analyze a class of estimators based on a convex relaxation for solving highdimensional matrix decomposition problems. The observations are the noisy realizations of the sum of ...
Alekh Agarwal, Sahand Negahban, Martin J. Wainwrig...