Many stochastic optimization algorithms work by estimating the gradient of the cost function on the fly by sampling datapoints uniformly at random from a training set. However, the estimator mightâ€¦ (More)

Networks, as abstractions for representing complex relationships among entities, are central in the modeling and analysis of many large-scale human and technical systems, and they have applicationsâ€¦ (More)

An individualâ€™s decisions are often guided by those of his or her peers, i.e., neighbors in a social network. Presumably, being privy to the experiences of others aids in learning and decisionâ€¦ (More)

We propose a new statistical dictionary learning algorithm for sparse signals that is based on an Î±-stable innovation model. The parameters of the underlying modelâ€”that is, the atoms of theâ€¦ (More)

Coordinate descent methods minimize a cost function by updating a single decision variable (corresponding to one coordinate) at a time. Ideally, one would update the decision variable that yields theâ€¦ (More)