More about HKUST
Modern Stochastic Optimization Methods for Big Data Machine Leraning
Speaker: Dr. Tong ZHANG Tencent AI Lab Title: "Modern Stochastic Optimization Methods for Big Data Machine Leraning" Date: Friday, 2 Nov 2018 Time: 3:00pm - 4:00pm Venue: Lecture Theater F (near lift 25/26), HKUST Abstract: In classical optimization, one needs to calculate a full (deterministic) gradient of the objective function at each step, which can be extremely costly for modem applications of big data machine learning. A remedy to this problem is to approximate each full gradient with a random sample over the data. This approach reduces the computational cost at each step, but introduces statistical variance. In this talk, I will present some recent progresses on applying variance reduction techniques previously developed for statistical Monte Carlo methods to this new problem setting. The resulting stochastic optimization methods are highly effective for practical big data problems in machine learning, and the new methods have strong theoretical guarantees that significantly improve the computational lower bounds of classical optimization algorithms. Collaborators: Rie Johnson, Shai Shalev-Schwartz, Jialei Wang