A Wasserstein Geometric Framework for Hebbian Plasticity

• URL: http://arxiv.org/abs/2604.16052v1
• Date: Fri, 17 Apr 2026 13:27:22 GMT
• Title: A Wasserstein Geometric Framework for Hebbian Plasticity
• Abstract summary: We introduce a geometric theory of Hebbian plasticity in which memory states are modeled as probability measures evolving through Wasserstein minimizing movements.<n>This variational structure induces a fundamental separation between internal and observable dynamics.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We introduce the Tan-HWG framework (Hebbian-Wasserstein-Geometry), a geometric theory of Hebbian plasticity in which memory states are modeled as probability measures evolving through Wasserstein minimizing movements. Hebbian learning rules are formalized as Hebbian energies satisfying a sequential stability condition, ensuring well-posed fiberwise JKO updates, optimal-transport realizations, and an energy descent inequality. This variational structure induces a fundamental separation between internal and observable dynamics. Internal memory states evolve along Wasserstein geodesics in a latent curved space, while observable quantities, such as effective synaptic weights, arise through geometric projection maps into external spaces. Simplicial projections recover classical affine schemes (including exponential moving averages and mirror descent), while revealing synaptic competition and pruning as geometric consequences of mass redistribution. Hilbertian projections provide a geometric account of phase alignment and multi-scale coherence. Classical neural networks appear as flat projections of this curved dynamics, while the framework naturally accommodates richer distributional representations, including structural weights and embedding memories, and their spectral extensions in complex internal spaces. Under mild Lipschitz regularity assumptions, including a quasi-stationary "sleep-mode" regime, we establish the existence of continuous-time limit curves. This yields a variational formulation of memory consolidation as a perturbed Wasserstein gradient flow. The framework thus provides a unified geometric foundation for synaptic plasticity, representation dynamics, and context-dependent computation.

Related papers

• Learning to Tessellate: Point Cloud Generation via Recursive Spectral Partitioning [58.130498928480456]
  We present PointRSP, an autoregressive framework that reformulates point cloud generation as a topology-preserving tessellation process.<n>PointRSP achieves state-of-the-art performance in generation quality and diversity, demonstrating strong generalization across complex 3D topologies.
  arXiv  Detail & Related papers  (2026-08-03T16:11:43Z)
• The Geometry of Quantum Complexity in Open Systems [0.0]
  We extend Nielsen's geometric approach for quantum complexity from closed to open quantum systems.<n>We analyze several physically motivated examples, including a single qubit subject to depolarizing and amplitude-damping channels.
  arXiv  Detail & Related papers  (2026-07-09T12:36:22Z)
• Engineering Quantum Many-Body Scars through Lattice Geometry [0.0028001975341488856]
  We show that lattice geometry alone can serve as a powerful and experimentally accessible control for inducing and enhancing scarring.<n>By transforming a one-dimensional chain into a quasi-one-dimensional triangle-decorated lattice, we find that the fully polarized state exhibits pronounced fidelity revivals, slow entanglement growth, and strong overlap with a tower of weakly entangled eigenstates.
  arXiv  Detail & Related papers  (2026-05-06T18:00:01Z)
• Generative Path-Finding Method for Wasserstein Gradient Flow [4.372661069805067]
  We propose a generative path finding framework for Wasserstein gradient paths.<n>GenWGP learns a generative flow that transports mass from an initial density to an unknown equilibrium distribution.<n>Experiments on Fokker Planck and aggregation type problems show that GenWGP matches or exceeds high fidelity reference solutions.
  arXiv  Detail & Related papers  (2026-04-13T14:22:20Z)
• Geometric Foundations of Stochastic and Quantum Dynamics [0.0]
  Noise, diffusion, path probabilities, fluctuation theorems, and entropy production arise from the intrinsic geometry of an evolving manifold.<n>We show that behaviour, irreversity, and quantum transition amplitudes are unified within the moving manifold framework.
  arXiv  Detail & Related papers  (2026-03-30T11:12:47Z)
• Geometric Quantum Mechanics in a Symplectic Framework: Metric-Affine Extensions and Deformed Quantum Dynamics [0.0]
  We introduce an extension in which the symplectic structure is allowed to couple to a metric-affine background geometry.<n>We show that, under suitable conditions, the deformed structure remains symplectic and defines a well-posed Hamiltonian system.
  arXiv  Detail & Related papers  (2026-03-22T12:47:16Z)
• Geometry and quantum brachistochrone analysis of multiple entangled spin-1/2 particles under all-range Ising interaction [0.0]
  We present a unified geometric and dynamical framework for a physical system consisting of $n$ spin-$1/2$ particles with all-range Ising interaction.<n>Our analysis reveals that the system evolves over a smooth, compact, two-dimensional manifold with spherical topology.<n>We explore the role of entanglement in shaping the state space geometry, modulating geometric phase, and controlling evolution speed and brachistochrone time.
  arXiv  Detail & Related papers  (2025-12-24T19:37:07Z)
• Learning Latent Graph Geometry via Fixed-Point Schrödinger-Type Activation: A Theoretical Study [1.1745324895296467]
  We develop a unified theoretical framework for neural architectures with internal representations evolving as stationary states of dissipative Schr"odinger-type dynamics on learned latent graphs.<n>We prove existence, uniqueness, and smooth dependence of equilibria, and show that the dynamics are equivalent under the Bloch map to norm-preserving Landau--Lifshitz flows.<n>The resulting model class provides a compact, geometrically interpretable, and analytically tractable foundation for learning latent graph geometry via fixed-point Schr"odinger-type activations.
  arXiv  Detail & Related papers  (2025-07-27T00:35:15Z)
• Why Neural Network Can Discover Symbolic Structures with Gradient-based Training: An Algebraic and Geometric Foundation for Neurosymbolic Reasoning [73.18052192964349]
  We develop a theoretical framework that explains how discrete symbolic structures can emerge naturally from continuous neural network training dynamics.<n>By lifting neural parameters to a measure space and modeling training as Wasserstein gradient flow, we show that under geometric constraints, the parameter measure $mu_t$ undergoes two concurrent phenomena.
  arXiv  Detail & Related papers  (2025-06-26T22:40:30Z)
• Geometric Trajectory Diffusion Models [58.853975433383326]
  Generative models have shown great promise in generating 3D geometric systems. Existing approaches only operate on static structures, neglecting the fact that physical systems are always dynamic in nature. We propose geometric trajectory diffusion models (GeoTDM), the first diffusion model for modeling the temporal distribution of 3D geometric trajectories.
  arXiv  Detail & Related papers  (2024-10-16T20:36:41Z)
• Geometric Phase of a Transmon in a Dissipative Quantum Circuit [44.99833362998488]
  We study the geometric phases acquired by a paradigmatic setup: a transmon coupled to a superconductor resonating cavity. In the dissipative model, the non-unitary effects arise from dephasing, relaxation, and decay of the transmon coupled to its environment. Our approach enables a comparison of the geometric phases obtained in these models, leading to a thorough understanding of the corrections introduced by the presence of the environment.
  arXiv  Detail & Related papers  (2024-01-22T16:41:00Z)
• Geometric Neural Diffusion Processes [55.891428654434634]
  We extend the framework of diffusion models to incorporate a series of geometric priors in infinite-dimension modelling. We show that with these conditions, the generative functional model admits the same symmetry.
  arXiv  Detail & Related papers  (2023-07-11T16:51:38Z)
• Geometric phase in a dissipative Jaynes-Cummings model: theoretical explanation for resonance robustness [68.8204255655161]
  We compute the geometric phases acquired in both unitary and dissipative Jaynes-Cummings models. In the dissipative model, the non-unitary effects arise from the outflow of photons through the cavity walls. We show the geometric phase is robust, exhibiting a vanishing correction under a non-unitary evolution.
  arXiv  Detail & Related papers  (2021-10-27T15:27:54Z)
• A Unifying and Canonical Description of Measure-Preserving Diffusions [60.59592461429012]
  A complete recipe of measure-preserving diffusions in Euclidean space was recently derived unifying several MCMC algorithms into a single framework. We develop a geometric theory that improves and generalises this construction to any manifold.
  arXiv  Detail & Related papers  (2021-05-06T17:36:55Z)

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.