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...
—Secure Computation (SC) enables secure distributed computation of arbitrary functions of private inputs. It has many useful applications, e.g. benchmarking or auctions. Several ...
Abstract— We consider the approximate sparse recovery problem, where the goal is to (approximately) recover a highdimensional vector x ∈ Rn from its lower-dimensional sketch Ax...
Matrix factorization has many applications in computer vision. Singular Value Decomposition (SVD) is the standard algorithm for factorization. When there are outliers and missing ...
Dimensionality reduction plays an important role in many machine learning and pattern recognition tasks. In this paper, we present a novel dimensionality reduction algorithm calle...