On expected signatures and signature cumulants in semimartingale models

2024/08/09 by Friz, Peter K., Hager, Paul P., Tapia, Nikolas · 2 citations
#60E10 #60G44 #60G48 #60G51 #60J76 #60L10 #60L90 #FOS: Computer and information sciences #FOS: Mathematics #Machine Learning (stat.ML) #Probability (math.PR)

paper · doi:10.48550/arxiv.2408.05085

Abstract

The concept of signatures and expected signatures is vital in data science, especially for sequential data analysis. The signature transform, a Cartan type development, translates paths into high-dimensional feature vectors, capturing their intrinsic characteristics. Under natural conditions, the expectation of the signature determines the law of the signature, providing a statistical summary of the data distribution. This property facilitates robust modeling and inference in machine learning and stochastic processes. Building on previous work by the present authors [Unified signature cumulants and generalized Magnus expansions, FoM Sigma '22] we here revisit the actual computation of expected signatures, in a general semimartingale setting. Several new formulae are given. A log-transform of (expected) signatures leads to log-signatures (signature cumulants), offering a significant reduction in complexity.

Cited by

• Expected signatures via partial integration, coordinate change and symmetrization
• Exponentially Fading Memory Signature

Related

• Learning with Expected Signatures: Theory and Applications
• Unified Signature Cumulants and Generalized Magnus Expansions
• Expected Signature Kernels for Lévy Rough Paths
• Signature Methods in Machine Learning
• Embedding and learning with signatures