1 code implementation • 19 Jan 2022 • Christian Bayer, Peter K. Friz, Nikolas Tapia
Using rough path techniques, we provide a priori estimates for the output of Deep Residual Neural Networks in terms of both the input data and the (trained) network weights.
no code implementations • 5 Feb 2021 • Peter K. Friz, Paul Hager, Nikolas Tapia
The signature of a path can be described as its full non-commutative exponential.
Probability 60L10, 60L90, 60E10, 60G44, 60G48, 60G51, 60J76
1 code implementation • 10 Dec 2020 • Joscha Diehl, Rosa Preiß, Michael Ruddy, Nikolas Tapia
Geometric features, robust to noise, of curves in Euclidean space are of great interest for various applications such as machine learning and image analysis.
Differential Geometry Algebraic Geometry 60L10, 14L24
no code implementations • 8 Dec 2020 • Joscha Diehl, Kurusch Ebrahimi-Fard, Nikolas Tapia
We explore the algebraic properties of a generalized version of the iterated-sums signature, inspired by previous work of F.~Kir\'aly and H.~Oberhauser.
1 code implementation • 17 Sep 2020 • Joscha Diehl, Kurusch Ebrahimi-Fard, Nikolas Tapia
Aiming for a systematic feature-extraction from time series, we introduce the iterated-sums signature over arbitrary commutative semirings.
no code implementations • 14 Jun 2019 • Elena Celledoni, Pål Erik Lystad, Nikolas Tapia
Signatures provide a succinct description of certain features of paths in a reparametrization invariant way.
1 code implementation • 13 Jun 2019 • Joscha Diehl, Kurusch Ebrahimi-Fard, Nikolas Tapia
We show that these correspond to a certain family of iterated sums of the increments of the time series, known as quasisymmetric functions in the mathematics literature.