The information revolution is spawning systems that require very frequent decisions and provide high volumes of data concerning past outcomes. Fueling the design of algorithms used in such systems is…
Wednesday, March 26, 2014 at 3:00pm
Frank H. T. Rhodes Hall, 253
ORIE Colloquium: Stefanie Jegelka (UC Berkeley) - Efficient learning with combinatorial structure
Learning from complex data such…
For roughly six decades since the seminal paper of Robbins and Monro (1951), Stochastic Approximation has dominated the landscape of algorithms for solving root finding and optimization problems with…
ORIE Colloquium: Marina A. Epelman (Michigan) - A Column Generation-Based Algorithm for Volumetric Modulated Arc Therapy (VMAT) Treatment Plan Optimization
Tuesday, March 5, 2013 at 3:00pm
Frank H.…
Tuesday, April 17 at 4:15pm
Frank H.T. Rhodes Hall, 253
We analyze the efficiency of particular Markov chain methods used in Bayesian statistics, giving some of the first meaningful bounds on the…
Standard approaches to solving stochastic dynamic programs suffer from the curse of dimensionality. Taking advantage of structural properties such as convexity can help reduce the effect of dimension…