Convolutional Signature for Sequential Data

09/14/2020
by   Ming Min, et al.
0

Signature is an infinite graded sequence of statistics known to characterize geometric rough paths, which includes the paths with bounded variation. This object has been studied successfully for machine learning with mostly applications in low dimensional cases. In the high dimensional case, it suffers from exponential growth in the number of features in truncated signature transform. We propose a novel neural network based model which borrows the idea from Convolutional Neural Network to address this problem. Our model reduces the number of features efficiently in a data dependent way. Some empirical experiments are provided to support our model.

READ FULL TEXT

page 1

page 2

page 3

page 4

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
05/21/2019

Deep Signatures

The signature is an infinite graded sequence of statistics known to char...
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
04/19/2022

LORD: Lower-Dimensional Embedding of Log-Signature in Neural Rough Differential Equations

The problem of processing very long time-series data (e.g., a length of ...
research
11/10/2020

Neural Networks Optimally Compress the Sawbridge

Neural-network-based compressors have proven to be remarkably effective ...
research
11/29/2019

Embedding and learning with signatures

Sequential and temporal data arise in many fields of research, such as q...
research
04/02/2022

Path Development Network with Finite-dimensional Lie Group Representation

The path signature, a mathematically principled and universal feature of...

Please sign up or login with your details

Forgot password? Click here to reset