Metraipolis › archive › dc_3243ded33000

On two proofs of $d^2$ mixing of weighted Dikin walks — arXiv:2608.28566

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.28566
License (as archived)
CC0-1.0
Archived
2026-10-17T11:06:51.521Z
SHA-256 of the archived text
229476a9171d4cfb9c7518dc4e60cbdad2a8a3e714a40e7364f10b25a806cad4
Stable URL of this page
https://metraipolis.com/documento/dc_3243ded33000

How to cite

On two proofs of $d^2$ mixing of weighted Dikin walks — arXiv:2608.28566 — arXiv (en), https://arxiv.org/abs/2608.28566 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3243ded33000 (Metraipolis archive dc_3243ded33000, sha256 229476a9171d4cfb9c7518dc4e60cbdad2a8a3e714a40e7364f10b25a806cad4)
BibTeX
@misc{dc3243ded33000,
  title = {On two proofs of $d^2$ mixing of weighted Dikin walks — arXiv:2608.28566},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.28566},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3243ded33000; sha256 229476a9171d4cfb9c7518dc4e60cbdad2a8a3e714a40e7364f10b25a806cad4},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.28566. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We study the mixing time of weighted Dikin walks for sampling from exponential distributions on polytopes and truncated positive-semidefinite (PSD) cones. Our first result gives a general total-variation mixing bound under strong self-concordance, $\bar{\nu}$-symmetry, and mixed-trace regularity on the local metric. The key idea is to control the Metropolis--Hastings acceptance probability on a high-probability region rather than at every point. Applying this framework to the Lee--Sidford, Lewis-weight, and John metrics yields an $\widetilde O(d^2)$ mixing bound for sampling from polytopes, while applying it to a hybrid barrier yields an $\widetilde O(d^4)$ mixing bound for sampling from truncated PSD cones. Our second result establishes stronger $\chi^2$-divergence guarantees and pointwise acceptance control using a new fourth-order bootstrap condition. For a suitably scaled Lee--Sidford metric, this yields an $\widetilde O(d^2)$ mixing bound in $\chi^2$-divergence, improving on the previous $\widetilde O(d^{9/4})$ bound.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-31 in cs.LG).
Categorie arXiv: Data Structures and Algorithms (cs.DS) ; Machine Learning (cs.LG); Optimization and Control (math.OC); Probability (math.PR); Computation (stat.CO).
Pagina del lavoro: https://arxiv.org/abs/2608.28566 — 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 2026-10-17T10:50:25.862Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-31?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).