Speaker: Dr. Guillaume Rabusseau
Title: Machine Learning with Tensors for Structured Data
Abstract: Over the last few years, the machine learning community has shown a growing interest towards tensors. The most obvious connection between tensors and machine learning appears when the data has a natural tensor structure (e.g. videos, hyperspectral images...) but tensors can also arise as model parameters or as powerful tools to design efficient and consistent learning algorithms. In this talk, I will show how tensor methods can be leveraged for learning with structured data. I will first consider the case of tensor structured data and show how taking the tensor structure into account, rather than vectorizing the data before feeding it to the learning algorithm, can lead to better computational and generalization performances. The second part of the talk will be focused on learning with discrete structured data such as sequences, trees and graphs. I will show how the classical computational model of weighted automata is particularly suited to represent functions defined over syntactic objects in the context of machine learning. After outlining the fundamental connections between weighted automata, tensors (and tensor networks), and more classical learning models such as recurrent neural networks, I will present recent contributions showcasing the relevance of weighted automata for learning with structured data, as well as ongoing and future research directions.
Guillaume Rabusseau is an IVADO postdoctoral research fellow in the Reasoning and Learning Lab at McGill University, where he works with Prakash Panangaden, Joelle Pineau and Doina Precup. His research interests lie at the intersection of theoretical computer science and machine learning. He obtained his PhD in computer science in 2016 at Aix-Marseille University under the supervision of François Denis and Hachem Kadri. His work revolves around exploring inter-connections between tensors and machine learning and developing efficient learning methods for structured data relying on linear and multilinear algebra.