Embedding and learning with signatures

11/29/2019
by   Adeline Fermanian, et al.
0

Sequential and temporal data arise in many fields of research, such as quantitative finance, medicine, or computer vision. The present article is concerned with a novel approach for sequential learning, called the signature method, and rooted in rough path theory. Its basic principle is to represent multidimensional paths by a graded feature set of their iterated integrals, called the signature. This approach relies critically on an embedding principle, which consists in representing discretely sampled data as paths, i.e., functions from [0,1] to R^d. After a survey of machine learning methodologies for signatures, we investigate the influence of embeddings on prediction accuracy with an in-depth study of three recent and challenging datasets. We show that a specific embedding, called lead-lag, is systematically better, whatever the dataset or algorithm used. Moreover, we emphasize through an empirical study that computing signatures over the whole path domain does not lead to a loss of local information. We conclude that, with a good embedding, the signature combined with a simple algorithm achieves results competitive with state-of-the-art, domain-specific approaches.

READ FULL TEXT
research
03/11/2016

A Primer on the Signature Method in Machine Learning

In these notes, we wish to provide an introduction to the signature meth...
research
05/17/2023

Nowcasting with signature methods

Key economic variables are often published with a significant delay of o...
research
04/04/2023

The insertion method to invert the signature of a path

The signature is a representation of a path as an infinite sequence of i...
research
06/26/2020

Computing the full signature kernel as the solution of a Goursat problem

Recently there has been an increased interested in the development of ke...
research
07/13/2017

Leveraging the Path Signature for Skeleton-based Human Action Recognition

Human action recognition in videos is one of the most challenging tasks ...
research
06/29/2022

Signature Methods in Machine Learning

Signature-based techniques give mathematical insight into the interactio...
research
09/14/2020

Convolutional Signature for Sequential Data

Signature is an infinite graded sequence of statistics known to characte...

Please sign up or login with your details

Forgot password? Click here to reset