Cohomological Obstructions to Global Counterfactuals: A Sheaf-Theoretic Foundation for Generative Causal Models

• URL: http://arxiv.org/abs/2603.17384v1
• Date: Wed, 18 Mar 2026 06:07:07 GMT
• Title: Cohomological Obstructions to Global Counterfactuals: A Sheaf-Theoretic Foundation for Generative Causal Models
• Abstract summary: We formalize structural causal models as cellular sheaves over Wasserstein spaces.<n>To ensure tractability, we introduce entropic regularization and derive the Entropic Wasserstein Causal Sheaf Laplacian.<n>Our framework successfully leverages thermodynamic noise to navigate topological barriers in high-dimensional scRNA-seq counterfactuals.
• Score: 7.073238726507493
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Current continuous generative models (e.g., Diffusion Models, Flow Matching) implicitly assume that locally consistent causal mechanisms naturally yield globally coherent counterfactuals. In this paper, we prove that this assumption fails fundamentally when the causal graph exhibits non-trivial homology (e.g., structural conflicts or hidden confounders). We formalize structural causal models as cellular sheaves over Wasserstein spaces, providing a strict algebraic topological definition of cohomological obstructions in measure spaces. To ensure computational tractability and avoid deterministic singularities (which we define as manifold tearing), we introduce entropic regularization and derive the Entropic Wasserstein Causal Sheaf Laplacian, a novel system of coupled non-linear Fokker-Planck equations. Crucially, we prove an entropic pullback lemma for the first variation of pushforward measures. By integrating this with the Implicit Function Theorem (IFT) on Sinkhorn optimality conditions, we establish a direct algorithmic bridge to automatic differentiation (VJP), achieving O(1)-memory reverse-mode gradients strictly independent of the iteration horizon. Empirically, our framework successfully leverages thermodynamic noise to navigate topological barriers ("entropic tunneling") in high-dimensional scRNA-seq counterfactuals. Finally, we invert this theoretical framework to introduce the Topological Causal Score, demonstrating that our Sheaf Laplacian acts as a highly sensitive algebraic detector for topology-aware causal discovery.

Related papers

• Exact Leg-Cut Influence Functional and Emergence of Gaussian Entanglement Theory in a Statistical-Dressing Ladder Model [0.0]
  We present an exact lattice formulation showing how non-Gaussian lattice-scale correlations are discarded under coarse-graining.<n>We show how highly non-Gaussian lattice states evolve toward their quadratic continuum form under coarse-graining.
  arXiv  Detail & Related papers  (2026-06-24T10:29:12Z)
• Topological Flow Matching [56.16372813551555]
  Flow matching is a powerful generative modeling framework, valued for its simplicity and strong empirical performance.<n>We introduce topological flow matching, a topology-aware generalization of flow matching.<n>We demonstrate its effectiveness on diverse structured datasets, including brain fMRIs, ocean currents, seismic events, and traffic flows.
  arXiv  Detail & Related papers  (2026-06-14T16:29:33Z)
• Generating function for Hermitian and non-Hermitian models [8.953650378946817]
  We show how boundary conditions and impurities determine the location of zeros in non-Hermitian systems.<n>Inspired by generating-function techniques widely used in discrete mathematics, our results establish a direct connection between non-Hermitian physics and recurrence relations.
  arXiv  Detail & Related papers  (2026-03-27T15:32:14Z)
• The Geometric Price of Discrete Logic: Context-driven Manifold Dynamics of Number Representations [6.414826816896125]
  Large language models (LLMs) generalize smoothly across continuous semantic spaces, yet strict logical reasoning demands the formation of discrete decision boundaries.<n>We argue that task context operates as a non-isometric dynamical operator that enforces a necessary "topological distortion"<n>We validate this geometric evolution across a gradient of tasks, from simple mapping to complex primality testing.
  arXiv  Detail & Related papers  (2026-03-24T13:41:57Z)
• The Causal Uncertainty Principle: Manifold Tearing and the Topological Limits of Counterfactual Interventions [7.073238726507493]
  Judea Pearl's do-calculus provides a foundation for causal inference, but its translation to continuous generative models remains fraught with geometric challenges.<n>We define the Counterfactual Event Horizon and prove the Manifold Tearing Theorem.<n>We introduce Geometry-Aware Causal Flow (GACF), a scalable algorithm that utilizes a topological radar to bypass manifold tearing.
  arXiv  Detail & Related papers  (2026-03-18T06:07:35Z)
• Beyond Attention: True Adaptive World Models via Spherical Kernel Operator [0.0]
  We introduce Spherical Kernel, a framework that replaces standard attention.<n>SKO mathematically decouples the true environmental transition dynamics from the biased observation frequency of the agent.<n> Empirical evaluations confirm that SKO significantly accelerates convergence and outperforms standard attention baselines in autoregressive language modeling.
  arXiv  Detail & Related papers  (2026-02-25T21:51:34Z)
• Deep Sequence Modeling with Quantum Dynamics: Language as a Wave Function [0.0]
  We introduce a sequence modeling framework in which the latent state is a complex-valued wave function evolving on a finite-dimensional Hilbert space under a learned, time-dependent Hamiltonian.<n> Token probabilities are extracted using the Born rule, a quadratic measurement operator that couples magnitudes and relative phases.<n>We derive a continuity equation for the latent probability mass, yielding conserved pairwise currents that serve as a built-in diagnostic.
  arXiv  Detail & Related papers  (2026-02-24T23:42:18Z)
• Riemannian Flow Matching for Disentangled Graph Domain Adaptation [51.98961391065951]
  Graph Domain Adaptation (GDA) typically uses adversarial learning to align graph embeddings in Euclidean space.<n>DisRFM is a geometry-aware GDA framework that unifies embedding and flow-based transport.
  arXiv  Detail & Related papers  (2026-01-31T11:05:35Z)
• Manifold Percolation: from generative model to Reinforce learning [0.26905021039717986]
  Generative modeling is typically framed as learning mapping rules, but from an observer's perspective without access to these rules, the task becomes disentangling the geometric support from the probability distribution.<n>We propose that continuum percolation is uniquely suited to this support analysis, as the sampling process effectively projects high-dimensional density estimation onto a geometric counting problem on the support.
  arXiv  Detail & Related papers  (2025-11-25T17:12:42Z)
• From Chern to Winding: Topological Invariant Correspondence in the Reduced Haldane Model [0.4249842620609682]
  We present an exact analytical investigation of the topological properties and edge states of the Haldane model defined on a honeycomb lattice with zigzag edges.<n>We show that the $nu$ exactly reproduces the Chern number of the parent model in the topologically nontrivial phase.<n>Our analysis further reveals the critical momentum $ k_c $ where edge states traverse the bulk energy gap.
  arXiv  Detail & Related papers  (2025-05-26T19:11:43Z)
• Preconditioned Langevin Dynamics with Score-Based Generative Models for Infinite-Dimensional Linear Bayesian Inverse Problems [4.2223436389469144]
  Langevin dynamics driven by score-based generative models (SGMs) acting as priors, formulated directly in function space.<n>We derive, for the first time, error estimates that explicitly depend on the approximation error of the score.<n>As a consequence, we obtain sufficient conditions for global convergence in Kullback-Leibler divergence on the underlying function space.
  arXiv  Detail & Related papers  (2025-05-23T18:12:04Z)
• Causal Modeling with Stationary Diffusions [89.94899196106223]
  We learn differential equations whose stationary densities model a system's behavior under interventions. We show that they generalize to unseen interventions on their variables, often better than classical approaches. Our inference method is based on a new theoretical result that expresses a stationarity condition on the diffusion's generator in a reproducing kernel Hilbert space.
  arXiv  Detail & Related papers  (2023-10-26T14:01:17Z)
• 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)
• Models of zero-range interaction for the bosonic trimer at unitarity [91.3755431537592]
  We present the construction of quantum Hamiltonians for a three-body system consisting of identical bosons mutually coupled by a two-body interaction of zero range. For a large part of the presentation, infinite scattering length will be considered.
  arXiv  Detail & Related papers  (2020-06-03T17:54:43Z)
• Dynamical solitons and boson fractionalization in cold-atom topological insulators [110.83289076967895]
  We study the $mathbbZ$ Bose-Hubbard model at incommensurate densities. We show how defects in the $mathbbZ$ field can appear in the ground state, connecting different sectors. Using a pumping argument, we show that it survives also for finite interactions.
  arXiv  Detail & Related papers  (2020-03-24T17:31:34Z)

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.