Talk by Dr. Rose Yu (Caltech)

Speaker: Dr. Rose Yu (http://roseyu.com/)

Title: Learning from Large-scale Time Series with Tensors

Abstract:
In many real-world applications, such as transportation, climate science and social
media, machine learning is applied on large-scale time series data. Such data is often
high-dimensional, and demonstrates complex correlation structures. Tensors, as
generalizations of vectors and matrices, provide a natural and scalable framework for
higher-order correlation modeling and dimension reduction. In this talk, I will
demonstrate how to efficiently learn from large-scale time series data with tensors. I will
present some recent results on 1) fast structure learning with Low-Rank Tensor Regression
and 2) long-term forecasting with High-Order Tensor RNNs, applied on traffic and climate
data. I will also discuss the challenges of learning from large-scale time series.

Bio:
Qi (Rose) Yu is a postdoctoral researcher in the Department of Computing and
Mathematical Sciences at Caltech. She will be an Assistant Professor in Northeastern
University College of Computer and Information Science starting Fall 2018. Previously,
She earned her Ph.D. in Computer Science at the University of Southern California and
was a visiting researcher at Stanford University.
Her research focuses on machine learning for large-scale time series and
spatiotemporal data, and is motivated by a range of applications, in particular
computational sustainability. She is the recipient of the USC Best Dissertation Award, “MIT
Rising Stars in EECS”, SIGKDD scholarship, and Annenberg fellowship.