Privacy Aware Learning
We study statistical risk minimization problems under a privacy model in which the data is kept confidential even from the learner. In this local privacy framework, we establish...
We study statistical risk minimization problems under a privacy model in which the data is kept confidential even from the learner. In this local privacy framework, we establish...
We present a new family of subgradient methods that dynamically incorporate knowledge of the geometry of the data observed in earlier iterations to perform more informative grad...
We describe efficient algorithms for projecting a vector onto the ℓ1-ball. We present two methods for projection. The first performs exact projection in O(n) expected time, wher...
We present a new method for regularized convex optimization and analyze it under both online and stochastic optimization settings. In addition to unifying previously known first...
h-index: Number of publications with at least h citations each.