5 papers
Anomaly Search Over Many Sequences With Switching Costs
Matthew Ubl, Benjamin D. Robinson, Matthew T. Hale
This paper considers the quickest search problem to identify anomalies among large numbers of data streams. These streams can model, for example, disjoint regions monitored by a mo…
Linear Regularizers Enforce the Strict Saddle Property
Matthew Ubl, Kasra Yazdani, Matthew T. Hale
Satisfaction of the strict saddle property has become a standard assumption in non-convex optimization, and it ensures that many first-order optimization algorithms will almost alw…
Faster Asynchronous Nonconvex Block Coordinate Descent with Locally Chosen Stepsizes
Matthew Ubl, Matthew T. Hale
Distributed nonconvex optimization problems underlie many applications in learning and autonomy, and such problems commonly face asynchrony in agents' computations and communicatio…
Totally Asynchronous Large-Scale Quadratic Programming: Regularization, Convergence Rates, and Parameter Selection
Matthew Ubl, Matthew T. Hale
Quadratic programs arise in robotics, communications, smart grids, and many other applications. As these problems grow in size, finding solutions becomes more computationally deman…
Totally Asynchronous Distributed Quadratic Programming with Independent Stepsizes and Regularizations
Matthew Ubl, Matthew Hale
Quadratic programs arise in robotics, communications, smart grids, and many other applications. As these problems grow in size, finding solutions becomes much more computationally…