Section: Partnerships and Cooperations
International Initiatives
BigFOKS2

Title: Learning from Big Data: FirstOrder methods for Kernels and Submodular functions

International Partner (Institution  Laboratory  Researcher):

See also: mllab.csa.iisc.ernet.in/indofrench.html

Recent advances in sensor technologies have resulted in large amounts of data being generated in a wide array of scientific disciplines. Deriving models from such large datasets, often known as “Big Data”, is one of the important challenges facing many engineering and scientific disciplines. In this proposal we investigate the problem of learning supervised models from Big Data, which has immediate applications in Computational Biology, Computer vision, Natural language processing, Web, Ecommerce, etc., where specific structure is often present and hard to take into account with current algorithms. Our focus will be on the algorithmic aspects. Often supervised learning problems can be cast as convex programs. The goal of this proposal will be to derive firstorder methods which can be effective for solving such convex programs arising in the BigData setting. Keeping this broad goal in mind we investigate two foundational problems which are not well addressed in existing literature. The first problem investigates Stochastic Gradient Descent Algorithms in the context of Firstorder methods for designing algorithms for Kernel based prediction functions on Large Datasets. The second problem involves solving discrete optimization problems arising in Submodular formulations in Machine Learning, for which firstorder methods have not reached the level of speed required for practical applications (notably in computer vision).