English

On Generation in Metric Spaces

Machine Learning 2026-02-10 v1 Machine Learning

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 (ε,ε)(\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 2\ell^2, all notions of generation may fail abruptly as the novelty parameters vary.

Cite

@article{arxiv.2602.07710,
  title  = {On Generation in Metric Spaces},
  author = {Jiaxun Li and Vinod Raman and Ambuj Tewari},
  journal= {arXiv preprint arXiv:2602.07710},
  year   = {2026}
}
R2 v1 2026-07-01T10:26:17.666Z