Seminar series
Date
Fri, 07 Jun 2019
Time
15:00 -
15:30
Location
N3.12
Speaker
Ilya Chevyrev
Organisation
(Oxford University)
In this talk I will introduce the concept of the path signature and motivate its recent use in analysis of time-ordered data. I will then describe a new feature map for barcodes in persistent homology by first realizing each barcode as a path in a vector space, and then computing its signature which takes values in the tensor algebra over that vector space. The composition of these two operations — barcode to path, path to tensor series — results in a feature map that has several desirable properties for statistical learning, such as universality and characteristicness.