Nonlinear Independent Component Analysis for Continuous-Time Signals

02/04/2021
by   Harald Oberhauser, et al.
0

We study the classical problem of recovering a multidimensional source process from observations of nonlinear mixtures of this process. Assuming statistical independence of the coordinate processes of the source, we show that this recovery is possible for many popular models of stochastic processes (up to order and monotone scaling of their coordinates) if the mixture is given by a sufficiently differentiable, invertible function. Key to our approach is the combination of tools from stochastic analysis and recent contrastive learning approaches to nonlinear ICA. This yields a scalable method with widely applicable theoretical guarantees for which our experiments indicate good performance.

READ FULL TEXT
research
06/09/2021

Independent mechanism analysis, a new concept?

Independent component analysis provides a principled framework for unsup...
research
07/24/2023

Extending Path-Dependent NJ-ODEs to Noisy Observations and a Dependent Observation Framework

The Path-Dependent Neural Jump ODE (PD-NJ-ODE) is a model for predicting...
research
01/13/2020

WICA: nonlinear weighted ICA

Independent Component Analysis (ICA) aims to find a coordinate system in...
research
06/28/2023

Identifiability of Discretized Latent Coordinate Systems via Density Landmarks Detection

Disentanglement aims to recover meaningful latent ground-truth factors f...
research
10/14/2022

Provable Subspace Identification Under Post-Nonlinear Mixtures

Unsupervised mixture learning (UML) aims at identifying linearly or nonl...
research
05/20/2016

Unsupervised Feature Extraction by Time-Contrastive Learning and Nonlinear ICA

Nonlinear independent component analysis (ICA) provides an appealing fra...
research
03/03/2021

Contrastive learning of strong-mixing continuous-time stochastic processes

Contrastive learning is a family of self-supervised methods where a mode...

Please sign up or login with your details

Forgot password? Click here to reset