RACVLGDec 8, 2020

Generalized iterated-sums signatures

arXiv:2012.04597v33 citations
AI Analysis

This work provides theoretical advancements in the algebraic understanding of iterated-sums signatures, which could be relevant for researchers working on time series analysis in machine learning.

This paper explores the algebraic properties of a generalized iterated-sums signature, recovering the character property of its associated linear map by using a deformed quasi-shuffle product. It also introduces three non-linear transformations on these signatures, relevant to Machine Learning applications.

We explore the algebraic properties of a generalized version of the iterated-sums signature, inspired by previous work of F.~Király and H.~Oberhauser. In particular, we show how to recover the character property of the associated linear map over the tensor algebra by considering a deformed quasi-shuffle product of words on the latter. We introduce three non-linear transformations on iterated-sums signatures, close in spirit to Machine Learning applications, and show some of their properties.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes