A reception will be held at 3:40 P.M. in the atrium outside the presentation room.
Theory for New Machine Learning Problems and Applications
Machine learning has recently achieved great empirical success. This comes along with new challenges, such as sophisticated models that lack rigorous analysis, simple algorithms with practical success on hard optimization problems, and handling large scale datasets under resource constraints. In this talk, Yingyu will present some of my work in addressing such challenges.
This first part of the talk will focus on learning semantic representations for text data. Recent advances in natural language processing build upon the approach of embedding words as low dimensional vectors. The fundamental observation that empirically justifies this approach is that these vectors can capture semantic relations. A probabilistic model for generating text is proposed to mathematically explain this observation and existing popular embedding algorithms. It also reveals surprising connections to classical notions such as Pointwise Mutual Information, and allows to design novel, simple, and practical algorithms for applications such as sentence embedding.
In the second part, he will describe his work on distributed unsupervised learning over large-scale data distributed over different locations. For the prototypical tasks clustering, Principal Component Analysis (PCA), and kernel PCA, Yingyu will present algorithms that have provable guarantees on solution quality, communication cost nearly optimal in key parameters, and strong empirical performance.