On the Identifiability of Nonlinear ICA: Sparsity and Beyond

• URL: http://arxiv.org/abs/2206.07751v5
• Date: Mon, 26 Feb 2024 04:10:37 GMT
• Title: On the Identifiability of Nonlinear ICA: Sparsity and Beyond
• Authors: Yujia Zheng, Ignavier Ng, Kun Zhang
• Abstract summary: How to make the nonlinear ICA model identifiable up to certain trivial indeterminacies is a long-standing problem in unsupervised learning. Recent breakthroughs reformulate the standard independence assumption of sources as conditional independence given some auxiliary variables. We show that under specific instantiations of such constraints, the independent latent sources can be identified from their nonlinear mixtures up to a permutation.
• Score: 20.644375143901488
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Nonlinear independent component analysis (ICA) aims to recover the underlying independent latent sources from their observable nonlinear mixtures. How to make the nonlinear ICA model identifiable up to certain trivial indeterminacies is a long-standing problem in unsupervised learning. Recent breakthroughs reformulate the standard independence assumption of sources as conditional independence given some auxiliary variables (e.g., class labels and/or domain/time indexes) as weak supervision or inductive bias. However, nonlinear ICA with unconditional priors cannot benefit from such developments. We explore an alternative path and consider only assumptions on the mixing process, such as Structural Sparsity. We show that under specific instantiations of such constraints, the independent latent sources can be identified from their nonlinear mixtures up to a permutation and a component-wise transformation, thus achieving nontrivial identifiability of nonlinear ICA without auxiliary variables. We provide estimation methods and validate the theoretical results experimentally. The results on image data suggest that our conditions may hold in a number of practical data generating processes.

Related papers

• Identifiable Feature Learning for Spatial Data with Nonlinear ICA [18.480534062833673]
  We introduce a new nonlinear ICA framework that employs latent components which apply naturally to data with higher-dimensional dependency structures. In particular, we develop a new learning and algorithm that extends variational methods to handle the combination of a deep neural network mixing function with the TP prior inducing computational efficacy.
  arXiv  Detail & Related papers  (2023-11-28T15:00:11Z)
• Generalizing Nonlinear ICA Beyond Structural Sparsity [15.450470872782082]
  identifiability of nonlinear ICA is known to be impossible without additional assumptions. Recent advances have proposed conditions on the connective structure from sources to observed variables, known as Structural Sparsity. We show that even in cases with flexible grouping structures, appropriate identifiability results can be established.
  arXiv  Detail & Related papers  (2023-11-01T21:36:15Z)
• Selective Nonparametric Regression via Testing [54.20569354303575]
  We develop an abstention procedure via testing the hypothesis on the value of the conditional variance at a given point. Unlike existing methods, the proposed one allows to account not only for the value of the variance itself but also for the uncertainty of the corresponding variance predictor.
  arXiv  Detail & Related papers  (2023-09-28T13:04:11Z)
• Learning Linear Causal Representations from Interventions under General Nonlinear Mixing [52.66151568785088]
  We prove strong identifiability results given unknown single-node interventions without access to the intervention targets. This is the first instance of causal identifiability from non-paired interventions for deep neural network embeddings.
  arXiv  Detail & Related papers  (2023-06-04T02:32:12Z)
• Discovering Latent Causal Variables via Mechanism Sparsity: A New Principle for Nonlinear ICA [81.4991350761909]
  Independent component analysis (ICA) refers to an ensemble of methods which formalize this goal and provide estimation procedure for practical application. We show that the latent variables can be recovered up to a permutation if one regularizes the latent mechanisms to be sparse.
  arXiv  Detail & Related papers  (2021-07-21T14:22:14Z)
• Independent mechanism analysis, a new concept? [3.2548794659022393]
  Identifiability can be recovered in settings where additional, typically observed variables are included in the generative process. We provide theoretical and empirical evidence that our approach circumvents a number of nonidentifiability issues arising in nonlinear blind source separation.
  arXiv  Detail & Related papers  (2021-06-09T16:45:00Z)
• Nonlinear Independent Component Analysis for Continuous-Time Signals [85.59763606620938]
  We study the classical problem of recovering a multidimensional source process from observations of mixtures of this process. We show that this recovery is possible for many popular models of processes (up to order and monotone scaling of their coordinates) if the mixture is given by a sufficiently differentiable, invertible function.
  arXiv  Detail & Related papers  (2021-02-04T20:28:44Z)
• Disentangling Observed Causal Effects from Latent Confounders using Method of Moments [67.27068846108047]
  We provide guarantees on identifiability and learnability under mild assumptions. We develop efficient algorithms based on coupled tensor decomposition with linear constraints to obtain scalable and guaranteed solutions.
  arXiv  Detail & Related papers  (2021-01-17T07:48:45Z)
• WICA: nonlinear weighted ICA [72.02008296553318]
  Independent Component Analysis (ICA) aims to find a coordinate system in which the components of the data are independent. We construct a new nonlinear ICA model, called WICA, which obtains better and more stable results than other algorithms.
  arXiv  Detail & Related papers  (2020-01-13T10:38:03Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.