Metraipolis › archive › dc_255f534ed0ed

Nonlocal Hamiltonian Dynamics on Sparse Lévy Graphs: Spectral Analysis and Multimodal Sampling — arXiv:2610.06904

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.06904
License (as archived)
CC0-1.0
Archived
2026-10-07T11:42:05.710Z
SHA-256 of the archived text
b9741c9b0dfc56a427a15ae63ec4972f03de8334184ba368e61c926ee157ddee
Stable URL of this page
https://metraipolis.com/documento/dc_255f534ed0ed

How to cite

Nonlocal Hamiltonian Dynamics on Sparse Lévy Graphs: Spectral Analysis and Multimodal Sampling — arXiv:2610.06904 — arXiv (en), https://arxiv.org/abs/2610.06904 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_255f534ed0ed (Metraipolis archive dc_255f534ed0ed, sha256 b9741c9b0dfc56a427a15ae63ec4972f03de8334184ba368e61c926ee157ddee)
BibTeX
@misc{dc255f534ed0ed,
  title = {Nonlocal Hamiltonian Dynamics on Sparse Lévy Graphs: Spectral Analysis and Multimodal Sampling — arXiv:2610.06904},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.06904},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_255f534ed0ed; sha256 b9741c9b0dfc56a427a15ae63ec4972f03de8334184ba368e61c926ee157ddee},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.06904. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We develop a sparse graph method for transporting probability mass toward multimodal target distributions through damped nonlocal Hamiltonian dynamics. The formulation combines logarithmic-mean mobility with symmetric Lévy-type interaction weights, coupling the evolving density to an edge momentum field. A graph constructed from nearest-neighbor connections and sampled long-range edges provides direct mass exchange between spatially separated regions. Once the graph is constructed, the density evolution is deterministic, and each update costs linear in the number of nodes and the long-range sampling budget. Linearization around the target distribution yields a damped oscillator governed by a weighted graph Laplacian. Its spectrum characterizes the interaction between nonlocal connectivity and inertia, with the Lévy exponent alpha tuning the nonlocal connectivity: the spectral gap determines the optimal asymptotic damping, while the largest eigenvalue governs the time-step stability. Experiments on synthetic multimodal distributions demonstrate improved mode balance and more stable mode coverage relative to first-order and MCMC baselines. The resulting framework provides a sparse implementation of nonlocal inertial density transport for sampling problems with low-dimensional spatial structure.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Dynamical Systems (math.DS) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.06904 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-07T11:19:24.860Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).