arXiv research

Introduces Exponentially Weighted Signature for better path representation.

Neural SDEs improve time series generation efficiency.

We give explicit representation formulas for marginally trapped submanifolds of co-dimension two in pseudo-Riemannian spaces with arbitrary signature and constant sectional curvature. This paper is dedicated to the memory of Franki Dillen, 1963-2013.

Path signatures improve hedging of exotic derivatives in non-Markovian models.

We study the spectral geometry of the Riemann curvature tensor for Pseudo-Riemannian manifolds and provide some examples illustrating the phenomena which can arise in the higher signature setting. Dedication: This paper is dedicated to the memory of our colleague Prof.G. Tsagas who studied the spectral geometry of Lapl…

Paper tackles DR problem with scalable signature-based approach.

Accelerates signature kernel computation for sequences.

New algorithms compute Volterra signature efficiently for time series analysis.

Volterra signature provides a clear, interpretable feature for history-dependent systems.

Neural RDEs extend CDEs to irregular time series.

Bayesian time series forecasting improves by dynamically adapting to recent information.

We introduce a simple analysis of the structural complexity of infinite-memory processes built from random samples of stationary, ergodic finite-memory component processes. Such processes are familiar from the well known multi-arm Bandit problem. We contrast our analysis with computation-theoretic and statistical infer…

Rough Transformers improve time series modeling with lower costs and better performance.

Gravitational wave memory increases faster than Brownian motion in early universe and astrophysical sources.

This paper examines Bitcoin's unique market properties and the leverage effect.

Paper introduces non-adversarial training for Neural SDEs using signature kernel scores.

Nowadays, multivariate time series data are increasingly collected in various real world systems, e.g., power plants, wearable devices, etc. Anomaly detection and diagnosis in multivariate time series refer to identifying abnormal status in certain time steps and pinpointing the root causes. Building such a system, how…

The paper revisits expected signatures in semimartingale models, providing new formulae and simplifying complexity.

New explanation of reservoir computing using random projections.

Defines knot signature invariant using G-signature theorem.

Deep signature/log-signature FBSDE algorithm improves accuracy and training time.

A well-known property of the signature of closed oriented 4n-dimensional manifolds is Novikov additivity, which states that if a manifold is split into two manifolds with boundary along an oriented smooth hypersurface, then the signature of the original manifold equals the sum of the signatures of the resulting manifol…

Maximum Levine-Tristram signature of torus knots follows a reduction formula.

New findings on mesh group-planes validate Signature-inverse Theorem under specific conditions.

Introduces flat discrete signatures for financial data analysis.

This is a sequel to the paper "The signature package on Witt spaces, I. Index classes" by the same authors. In the first part we investigated, via a parametrix construction, the regularity properties of the signature operator on a stratified Witt pseudomanifold, proving, in particular, that one can define a K-homology …

We define the Analytical signature, the Hodge signature and the de Rham signature for a foliated manifold with boundary with foliation transverse to the boundary. We show that all these signatures coincide and a Hirzebruch formula is valid.

Unifies 18 definitions of surprise, classifies them into four categories.

New methods price American options in rough volatility models.

The paper examines the consistency of Lasso regression applied to signature analysis of time series data.

Study signatures of torus links and their cores using Neumann's equivariant signatures and Hirzebruch's formula.

This paper extends the C*-signature to non-Witt spaces using noncommutative geometric methods.

Paper generalizes path signature using fractional calculus for improved machine learning.

We present a novel method for extracting cancer signatures by applying statistical risk models (http://ssrn.com/abstract=2732453) from quantitative finance to cancer genome data. Using 1389 whole genome sequenced samples from 14 cancers, we identify an "overall" mode of somatic mutational noise. We give a prescription …

pySigLib speeds up signature-based computations on CPUs and GPUs.

Efficiently computes sparse signature coefficients using kernels.

New method calculates signatures of biquotients.

Paper introduces branched signature model for efficient computation and data-driven applications.

Link signature limit depends on linking matrix under specific polynomial condition.

Develops a new family of signature-changing models on metric manifolds.

We prove that the signature of an even, symmetric form on a finite rank integral lattice, has signature divisible by 8, provided its associated linking form vanishes in the Witt group of linking forms. Our result generalizes the well know fact that an even, unimodular form has signature divisible by 8. We give applicat…

Paper confirms Kashaev's signature conjecture for links.

The paper defines signatures for Witt spaces with boundary and proves their equality.

Rough Transformers improve efficiency for medical time-series data.

Study finds infinitely many surface bundle types with zero signature.

In this note, we lay the groundwork for a new approach to the problem of group-signature classification of group actions on closed Riemann surfaces. This new approach first focuses on analyzing the low level arithmetic conditions on signatures before invoking the more complicated group theory. We provide the complete f…

A new graph signature invariant to graph automorphisms.

The study explains why signature methods work in commodity futures term structure classification.