On Generation in Metric Spaces
- URL: http://arxiv.org/abs/2602.07710v1
- Date: Sat, 07 Feb 2026 21:37:59 GMT
- Title: On Generation in Metric Spaces
- Authors: Jiaxun Li, Vinod Raman, Ambuj Tewari,
- Abstract summary: We study generation in separable metric instance spaces.<n>We introduce the $(varepsilon,varepsilon')$-closure dimension.<n>In general metric spaces, generatability can be highly scale-sensitive and metric-dependent.
- Score: 29.71858964413957
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: We study generation in separable metric instance spaces. We extend the language generation framework from Kleinberg and Mullainathan [2024] beyond countable domains by defining novelty through metric separation and allowing asymmetric novelty parameters for the adversary and the generator. We introduce the $(\varepsilon,\varepsilon')$-closure dimension, a scale-sensitive analogue of closure dimension, which yields characterizations of uniform and non-uniform generatability and a sufficient condition for generation in the limit. Along the way, we identify a sharp geometric contrast. Namely, in doubling spaces, including all finite-dimensional normed spaces, generatability is stable across novelty scales and invariant under equivalent metrics. In general metric spaces, however, generatability can be highly scale-sensitive and metric-dependent; even in the natural infinite-dimensional Hilbert space $\ell^2$, all notions of generation may fail abruptly as the novelty parameters vary.
Related papers
- Constant Metric Scaling in Riemannian Computation [0.31727619150610836]
We show how constant metric scaling can be introduced without altering the geometric structures on which these methods rely.<n>The goal of this note is purely expository and is intended to clarify how a global metric scale parameter can be introduced without altering the geometric structures on which these methods rely.
arXiv Detail & Related papers (2026-01-16T04:54:23Z) - Error-correcting codes and absolutely maximally entangled states for mixed dimensional Hilbert spaces [2.7214777196418645]
We introduce a stabiliser formalism for mixed dimensional Hilbert spaces.<n>We redefine entanglement measures for these Hilbert spaces and define absolutely maximally entangled states.<n>We provide examples of absolutely maximally entangled states in spaces of dimensions not previously known to have absolutely maximally entangled states.
arXiv Detail & Related papers (2025-10-20T07:21:33Z) - Local unambiguous unidentifiability, entanglement generation, and Hilbert space splitting [0.0]
We consider collections of mixed states supported on mutually orthogonal subspaces whose rank add up to the total dimension of the underlying Hilbert space.<n>No state from the set can be unambiguously identified by local operations and classical communication (LOCC) with non-zero success probability.<n>We show the necessary and sufficient condition for such a property to exist is that the states must be supported in entangled subspaces.
arXiv Detail & Related papers (2025-03-07T18:33:19Z) - Is magnitude 'generically continuous' for finite metric spaces? [0.0]
We show that magnitude is nowhere continuous on the Gromov-Hausdorff space of finite metric spaces.<n>Yet, we find evidence to suggest that it may be 'generically continuous', in the sense that generic Gromov-Hausdorff limits are preserved by magnitude.
arXiv Detail & Related papers (2025-01-15T12:01:41Z) - Topological nature of edge states for one-dimensional systems without symmetry protection [46.87902365052209]
We numerically verify and analytically prove a winding number invariant that correctly predicts the number of edge states in one-dimensional, nearest-neighbor (between unit cells)<n>Our winding number is invariant under unitary or similarity transforms.
arXiv Detail & Related papers (2024-12-13T19:44:54Z) - nSimplex Zen: A Novel Dimensionality Reduction for Euclidean and Hilbert
Spaces [0.5076419064097734]
Dimensionality reduction techniques map values from a high dimensional space to one with a lower dimension.
We introduce nSimplex Zen, a novel topological method of reducing dimensionality.
arXiv Detail & Related papers (2023-02-22T17:26:01Z) - Continuous percolation in a Hilbert space for a large system of qubits [58.720142291102135]
The percolation transition is defined through the appearance of the infinite cluster.
We show that the exponentially increasing dimensionality of the Hilbert space makes its covering by finite-size hyperspheres inefficient.
Our approach to the percolation transition in compact metric spaces may prove useful for its rigorous treatment in other contexts.
arXiv Detail & Related papers (2022-10-15T13:53:21Z) - 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) - Dimension Free Generalization Bounds for Non Linear Metric Learning [61.193693608166114]
We provide uniform generalization bounds for two regimes -- the sparse regime, and a non-sparse regime.
We show that by relying on a different, new property of the solutions, it is still possible to provide dimension free generalization guarantees.
arXiv Detail & Related papers (2021-02-07T14:47:00Z) - Geometry of Similarity Comparisons [51.552779977889045]
We show that the ordinal capacity of a space form is related to its dimension and the sign of its curvature.
More importantly, we show that the statistical behavior of the ordinal spread random variables defined on a similarity graph can be used to identify its underlying space form.
arXiv Detail & Related papers (2020-06-17T13:37:42Z) - Quantum Geometric Confinement and Dynamical Transmission in Grushin
Cylinder [68.8204255655161]
We classify the self-adjoint realisations of the Laplace-Beltrami operator minimally defined on an infinite cylinder.
We retrieve those distinguished extensions previously identified in the recent literature, namely the most confining and the most transmitting.
arXiv Detail & Related papers (2020-03-16T11:37:23Z)
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.