Unsupervised Disentanglement Without Compromises : How Functional Orthogonality Enforces Identifiability

• URL: http://arxiv.org/abs/2606.21385v1
• Date: Fri, 19 Jun 2026 12:47:07 GMT
• Title: Unsupervised Disentanglement Without Compromises : How Functional Orthogonality Enforces Identifiability
• Abstract summary: This paper explores unsupervised disentangled representation learning from a functional perspective.<n>We prove that this condition yields identifiability of general nonlinear generative models.
• Score: 46.784084625532984
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: This paper explores unsupervised disentangled representation learning from a functional perspective. We define latent concepts as factors that influence observations through locally orthogonal directions, formalized as an orthogonality constraint on the Jacobian of the generative mapping. We prove that this condition yields identifiability of general nonlinear generative models, without requiring statistical independence or causal assumptions, provided the latent domain admits all combinations of factor values. Experiments with orthogonality-regularized normalizing flows empirically confirm the theory, demonstrate reliable recovery of ground-truth factors, and shed light on the success of VAEs. These findings challenge the prevailing impossibility claims for unsupervised disentanglement and provide a principled alternative foundation.

Related papers

• Towards Unsupervised Causal Representation Learning via Latent Additive Noise Model Causal Autoencoders [1.9732490977700972]
  Unsupervised representation learning seeks to recover latent generative factors.<n>Disentangling causal variables from observational data is impossible without supervision.<n>We propose the Latent Additive Noise Model Causal Autoencoder (LANCA) as a strong inductive bias for unsupervised discovery.
  arXiv  Detail & Related papers  (2025-12-15T10:52:30Z)
• Mechanistic Independence: A Principle for Identifiable Disentangled Representations [7.550362088105815]
  Disentangled representations seek to recover latent factors of variation underlying observed data.<n>We introduce a unified framework in which disentanglement is achieved through mechanistic independence.
  arXiv  Detail & Related papers  (2025-09-26T10:58:03Z)
• Identifiable Latent Neural Causal Models [82.14087963690561]
  Causal representation learning seeks to uncover latent, high-level causal representations from low-level observed data. We determine the types of distribution shifts that do contribute to the identifiability of causal representations. We translate our findings into a practical algorithm, allowing for the acquisition of reliable latent causal representations.
  arXiv  Detail & Related papers  (2024-03-23T04:13:55Z)
• 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)
• On the Identifiability of Quantized Factors [33.12356885773274]
  We show that it is possible to recover quantized latent factors under a generic nonlinear diffeomorphism. We introduce this novel form of identifiability, termed quantized factor identifiability, and provide a comprehensive proof of the recovery of the quantized factors.
  arXiv  Detail & Related papers  (2023-06-28T16:10:01Z)
• 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)
• Nonparametric Identifiability of Causal Representations from Unknown Interventions [63.1354734978244]
  We study causal representation learning, the task of inferring latent causal variables and their causal relations from mixtures of the variables. Our goal is to identify both the ground truth latents and their causal graph up to a set of ambiguities which we show to be irresolvable from interventional data.
  arXiv  Detail & Related papers  (2023-06-01T10:51:58Z)
• Function Classes for Identifiable Nonlinear Independent Component Analysis [10.828616610785524]
  Unsupervised learning of latent variable models (LVMs) is widely used to represent data in machine learning. Recent work suggests that constraining the function class of such models may promote identifiability. We prove that a subclass of these transformations, conformal maps, is identifiable and provide novel theoretical results.
  arXiv  Detail & Related papers  (2022-08-12T17:58:31Z)
• 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)
• Invariance Principle Meets Information Bottleneck for Out-of-Distribution Generalization [77.24152933825238]
  We show that for linear classification tasks we need stronger restrictions on the distribution shifts, or otherwise OOD generalization is impossible. We prove that a form of the information bottleneck constraint along with invariance helps address key failures when invariant features capture all the information about the label and also retains the existing success when they do not.
  arXiv  Detail & Related papers  (2021-06-11T20:42:27Z)
• 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)

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.