
Abstract:
We prove a central limit theorem for a class of additive processes that arise naturally in the
theory of finite horizon Markov decision problems. The main theorem generalizes a…














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…


We give an efficient algorithm for computing a Cournot equilibrium when the producers are confined to integers, the inverse demand function is linear, and costs are quadratic. The method also…


Variational analysis has come of age. Long an elegant theoretical toolkit for variational mathematics and nonsmooth optimization, it now increasingly underpins the study of algorithms, and a rich…


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 as…


Friday, May 2
2:20 p.m. – Presentation – 253 Rhodes Hall
Philippe Rigollet
The statistical price to pay for computational efficiency in sparse PCA
Computational limitations of…


Tuesday, April 29, 2014 at 4:15pm
Frank H. T. Rhodes Hall, 253
ORIE Colloquium: Martin Skutella (TU Berlin)  An improved additive approximation for the ring loading problem
The ring loading problem…


Tuesday, February 4, 2014 at 4:15pm
Upson Hall, B17
ORIE Colloquium: John Duchi (UC Berkeley)  Machine Learning: a Discipline of Resource Tradeoffs
Joint colloquium with Computer Science.
How can…


Tuesday, May 6, 2014 at 4:15 PM [.ics]
253 Rhodes Hall
Alexander (Sasha) Rakhlin
Assistant Professor, Department of Statistics
Secondary appointment: Department of Computer & Information…


The study of firstorder methods has largely dominated research in continuous optimization for the last decade, yet still the range of problems for which optimal firstorder methods have been…
