Searcharxiv⌕ Search

arXiv · 2611.08030

Recovering the Length of a Path from its Signature

Abstract

We prove the length conjecture of J. Chang, T. Lyons and H. Ni for paths of bounded variation for arbitrary real Banach spaces and any reasonable tensor (algebra) norms. More precisely, we establish the missing lower bound and in this way show that the length of a tree-reduced path is recovered from the asymptotic behaviour of its normalised signature. The main technical argument uses the norm duality and shuffle algebra to express natural powers of polygonal length approximations as combinations of linear functionals acting on restricted signatures, which are then glued by suitable integrations into a linear functional of controlled growth acting on the full signature. In particular, the full proof combines tools of classical analysis and functional analysis, such as localisation by continuous cutoff functions, Stone-Weierstrass approximation of continuous functions by signature polynomials, the Hahn-Banach theorem and a support detection lemma for compactly supported real signed Borel measures.

Explore related subjects

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Felix Medwed. 2026-11-05. Recovering the Length of a Path from its Signature. https://arxiv.org/abs/2611.08030

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

On a characterization of spaces satisfying open mapping and equivalent theorems

We study open-mapping, continuous-inverse and closed-graph properties for maps whose domain and range belong to the same class of Hausdorff topological vector spaces. Quotient and graph stability imply equivalence of these properties. In the locally convex setting, we characterize barrelled infra-Pták spaces and barrelled Pták spaces as largest classes determined by the closed-graph property, Banach test spaces and appropriate nearly-open image conditions.

math.FA↗

A family of matrix flows converging to normal matrices

The celebrated Antezana-Pujals-Stojanoff Theorem states that the iterated Aluthge transforms of an arbitrary matrix converge to a normal matrix. We introduce a family of matrix flows that share this convergence property by defining them through ordinary differential equations. The family includes a continuous analogue of the Aluthge transform, as well as a differential equation discussed by Haagerup in the context of II$_1$ factors. We also examine the same type of flows in the setting of Hilbert space operators equipped with unitarily invariant norms.

math.FA↗

A Novel Two-Parameter Penalty: Relaxation Degree Analysis and Sparse Signal Recovery

In this article, we introduce a nonconvex two-parameter penalty function $P_{a,p}$, parameterized by $a\in(0,\infty)$ and $p\in(0,1]$, and the relaxation degree RD$_P$ for a separable nonconvex penalty function $P$. Based on $P_{a,p}$, we further propose the $P_{a,p}$ minimization framework for sparse signal recovery. This framework generalizes the TL1 minimization model established by S. Zhang and J. Xin (corresponding to the special case $p=1$) and provides a unified family of nonconvex penalty functions for sparse signal recovery. Using the sparse convex-combination technique, we establish both exact and stable sparse signal recovery under the restricted isometry property (RIP). To efficiently solve the resulting nonconvex optimization problem, we apply a modified iteratively re-weighted least squares method and the difference of convex functions algorithm (DCA) to develop the IRLSTLp algorithm for unconstrained $P_{a,p}$ minimization and prove some convergence results. Finally, numerical experiments compare recovery and runtime against single- and double-loop baselines, examine sensitivity to $(a,p)$, and assess the empirical correlation between RD$_{P_{a,p}}$ and recovery within the proposed family.

math.FA↗