Related papers: Operationalizing Quantized Disentanglement

Operationalizing Quantized Disentanglement

URL: http://arxiv.org/abs/2511.20927v1
Date: Tue, 25 Nov 2025 23:41:26 GMT
Title: Operationalizing Quantized Disentanglement
Authors: Vitoria Barin-Pacela, Kartik Ahuja, Simon Lacoste-Julien, Pascal Vincent,
Abstract summary: We develop a criterion for unsupervised disentanglement by encouraging axis-aligned discontinuities.<n>Discontinuities manifest as sharp changes in the estimated density of factors and form what we call cliffs.<n>We show that our method, Cliff, outperforms the baselines on all disentanglement benchmarks.
Score: 26.410344820790694
License: http://creativecommons.org/licenses/by/4.0/
Abstract: Recent theoretical work established the unsupervised identifiability of quantized factors under any diffeomorphism. The theory assumes that quantization thresholds correspond to axis-aligned discontinuities in the probability density of the latent factors. By constraining a learned map to have a density with axis-aligned discontinuities, we can recover the quantization of the factors. However, translating this high-level principle into an effective practical criterion remains challenging, especially under nonlinear maps. Here, we develop a criterion for unsupervised disentanglement by encouraging axis-aligned discontinuities. Discontinuities manifest as sharp changes in the estimated density of factors and form what we call cliffs. Following the definition of independent discontinuities from the theory, we encourage the location of the cliffs along a factor to be independent of the values of the other factors. We show that our method, Cliff, outperforms the baselines on all disentanglement benchmarks, demonstrating its effectiveness in unsupervised disentanglement.

Related papers

Operational Derivation of Born's Rule from Causal Consistency in Generalized Probabilistic Theories [0.0]
We show that any admissible state-to-probability map must be affine under mixing.<n>We identify Born's rule as a causal fixed point among admissible probabilistic laws.
arXiv Detail & Related papers (2025-12-14T10:50:42Z)
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)
Nonparametric Partial Disentanglement via Mechanism Sparsity: Sparse Actions, Interventions and Sparse Temporal Dependencies [58.179981892921056]
This work introduces a novel principle for disentanglement we call mechanism sparsity regularization. We propose a representation learning method that induces disentanglement by simultaneously learning the latent factors. We show that the latent factors can be recovered by regularizing the learned causal graph to be sparse.
arXiv Detail & Related papers (2024-01-10T02:38:21Z)
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)
Role of boundary conditions in the full counting statistics of topological defects after crossing a continuous phase transition [62.997667081978825]
We analyze the role of boundary conditions in the statistics of topological defects. We show that for fast and moderate quenches, the cumulants of the kink number distribution present a universal scaling with the quench rate.
arXiv Detail & Related papers (2022-07-08T09:55:05Z)
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)
Localisation in quasiperiodic chains: a theory based on convergence of local propagators [68.8204255655161]
We present a theory of localisation in quasiperiodic chains with nearest-neighbour hoppings, based on the convergence of local propagators. Analysing the convergence of these continued fractions, localisation or its absence can be determined, yielding in turn the critical points and mobility edges. Results are exemplified by analysing the theory for three quasiperiodic models covering a range of behaviour.
arXiv Detail & Related papers (2021-02-18T16:19:52Z)
Causal Expectation-Maximisation [70.45873402967297]
We show that causal inference is NP-hard even in models characterised by polytree-shaped graphs. We introduce the causal EM algorithm to reconstruct the uncertainty about the latent variables from data about categorical manifest variables. We argue that there appears to be an unnoticed limitation to the trending idea that counterfactual bounds can often be computed without knowledge of the structural equations.
arXiv Detail & Related papers (2020-11-04T10:25:13Z)
A Weaker Faithfulness Assumption based on Triple Interactions [89.59955143854556]
We propose a weaker assumption that we call $2$-adjacency faithfulness. We propose a sound orientation rule for causal discovery that applies under weaker assumptions.
arXiv Detail & Related papers (2020-10-27T13:04:08Z)
An Effective Way of Characterizing the Quantum Nonlocality [0.5156484100374059]
Nonlocality is a distinctive feature of quantum theory, which has been extensively studied for decades. It is found that the uncertainty principle determines the nonlocality of quantum mechanics.
arXiv Detail & Related papers (2020-08-14T14:27:59Z)

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