Amplitude and phase variation of point processes
From MaRDI portal
Abstract: We develop a canonical framework for the study of the problem of registration of multiple point processes subjected to warping, known as the problem of separation of amplitude and phase variation. The amplitude variation of a real random function corresponds to its random oscillations in the -axis, typically encapsulated by its (co)variation around a mean level. In contrast, its phase variation refers to fluctuations in the -axis, often caused by random time changes. We formalise similar notions for a point process, and nonparametrically separate them based on realisations of i.i.d. copies of the phase-varying point process. A key element in our approach is to demonstrate that when the classical phase variation assumptions of Functional Data Analysis (FDA) are applied to the point process case, they become equivalent to conditions interpretable through the prism of the theory of optimal transportation of measure. We demonstrate that these induce a natural Wasserstein geometry tailored to the warping problem, including a formal notion of bias expressing over-registration. Within this framework, we construct nonparametric estimators that tend to avoid over-registration in finite samples. We show that they consistently estimate the warp maps, consistently estimate the structural mean, and consistently register the warped point processes, even in a sparse sampling regime. We also establish convergence rates, and derive -consistency and a central limit theorem in the Cox process case under dense sampling, showing rate optimality of our structural mean estimator in that case.
Recommendations
- On the definition of phase and amplitude variability in functional data analysis
- Functional registration and local variations: identifiability, rank, and tuning
- Nonparametric registration to low-dimensional function spaces
- Combining registration and fitting for functional models
- Robust depth-based estimation in the time warping model
Cites work
- scientific article; zbMATH DE number 50540 (Why is no real title available?)
- scientific article; zbMATH DE number 3538605 (Why is no real title available?)
- scientific article; zbMATH DE number 1909499 (Why is no real title available?)
- A General Concept of Unbiasedness
- Alignment of curves by dynamic time warping
- Amplitude and phase variation of point processes
- An Introduction to the Theory of Point Processes
- Analysis of spike train data: alignment and comparisons using the extended Fisher-Rao metric
- Applied functional data analysis. Methods and case studies
- Barycenters in the Wasserstein space
- Combining registration and fitting for functional models
- Consistent estimates of deformed isotropic Gaussian random fields on the plane
- Curve Registration
- Curve alignment by moments
- Differential equation models for statistical functions
- Distribution's template estimate with Wasserstein metrics
- Estimating deformations of isotropic Gaussian random fields on the plane
- Estimating summary statistics in the spike-train space
- Functional data analysis for point processes with rare events
- Functional data analysis.
- Generative models for functional data using phase and amplitude separation
- Kernel Estimation of Rate Function for Recurrent Event Data
- Model estimation in nonlinear regression under shape invariance
- Nonparametric maximum likelihood estimation for shifted curves
- Nonparametric maximum likelihood estimation of the structural mean of a sample of curves
- Optimal maps for the multidimensional Monge-Kantorovich problem
- Pairwise curve synchronization for functional data
- Pairwise dynamic time warping for event data
- Probability. Theory and examples.
- Searching for Structure in Curve Sample
- Self-Modelling Warping Functions
- Sliced and Radon Wasserstein barycenters of measures
- Some asymptotic theory for the bootstrap
- Statistics of time warpings and phase variations
- Synchronizing sample curves nonparametrically
- Transforming spatial point processes into Poisson processes
- Weak homogenization of point processes by space deformations
Cited in
(32)- Spatial prediction and spatial dependence monitoring on georeferenced data streams
- On the definition of phase and amplitude variability in functional data analysis
- Randomized Wasserstein barycenter computation: resampling with statistical guarantees
- Towards optimal running timesfor optimal transport
- Wasserstein Regression
- Fréchet single index models for object response regression
- Fréchet means and Procrustes analysis in Wasserstein space
- Wasserstein \(F\)-tests and confidence bands for the Fréchet regression of density response curves
- Nonparametric Estimation of Repeated Densities with Heterogeneous Sample Sizes
- Wasserstein gradients for the temporal evolution of probability distributions
- Procrustes metrics on covariance operators and optimal transportation of Gaussian processes
- Empirical optimal transport on countable metric spaces: distributional limits and statistical applications
- On distributional autoregression and iterated transportation
- Monitoring for a change point in a sequence of distributions
- A fast solver for generalized optimal transport problems based on dynamical system and algebraic multigrid
- Penalization of barycenters in the Wasserstein space
- Continuous and atlas-free analysis of brain structural connectivity
- Additive functional regression for densities as responses
- Upper and lower risk bounds for estimating the Wasserstein barycenter of random measures on the real line
- Functional registration and local variations: identifiability, rank, and tuning
- Medoid splits for efficient random forests in metric spaces
- Amplitude recursions with an extra marked point
- Multimodal Bayesian registration of noisy functions using Hamiltonian Monte Carlo
- Wasserstein autoregressive models for density time series
- Functional data analysis: an introduction and recent developments
- Point process models for COVID-19 cases and deaths
- On quantum optimal transport
- Statistical analysis of functions on surfaces, with an application to medical imaging
- Amplitude and phase variation of point processes
- scientific article; zbMATH DE number 967322 (Why is no real title available?)
- Fréchet regression for random objects with Euclidean predictors
- Bayesian semiparametric modelling of phase-varying point processes
This page was built for publication: Amplitude and phase variation of point processes
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q282475)
