סמינר מחלקתי
Online Stochastic Optimization with a Moving Target
Prof. Assaf Zeevi
Abstract :
Stochastic approximation refers to a family of methods whose objective is to sequentially estimate the optimum point of a fixed yet unknown cost function whose observations are confounded by statistical noise. Since its inception in the 1950's, the method has been the subject of a voluminous literature and is widely used in a variety of application settings. In this talk we will develop some theory that attempts to expand the scope of stochastic approximation to non-stationary environments, i.e., when the cost function is allowed to change over time. Some (hopefully interesting) connections will be drawn to a recent strand of literature on online convex optimization, which studies the aforementioned problem in a so-called adversarial setting.
Joint work with Omar Besbes, Columbia University, and Yoni Gur, Stanford University.
ההרצאה תתקיים ביום שלישי 20.1.15, בשעה 14:00 בחדר 206, בנין וולפסון הנדסה, הפקולטה להנדסה, אוניברסיטת תל-אביב.