Metraipolis › archive › dc_456a4e303c87

Sharp spectral norm concentration of sparse random tensors — arXiv:2609.20520

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.20520
License (as archived)
CC0-1.0
Archived
2026-10-10T04:15:51.888Z
SHA-256 of the archived text
3719741a5c4865a2bd24fa730e093173b63c4a0dde34b8d3948a68c159c4162d
Stable URL of this page
https://metraipolis.com/documento/dc_456a4e303c87

How to cite

Sharp spectral norm concentration of sparse random tensors — arXiv:2609.20520 — arXiv (en), https://arxiv.org/abs/2609.20520 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_456a4e303c87 (Metraipolis archive dc_456a4e303c87, sha256 3719741a5c4865a2bd24fa730e093173b63c4a0dde34b8d3948a68c159c4162d)
BibTeX
@misc{dc456a4e303c87,
  title = {Sharp spectral norm concentration of sparse random tensors — arXiv:2609.20520},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.20520},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_456a4e303c87; sha256 3719741a5c4865a2bd24fa730e093173b63c4a0dde34b8d3948a68c159c4162d},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.20520. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We prove a sharp concentration inequality for the spectral norm of sparse random tensors with independent Bernoulli entries. Let $T$ be an order-$k$ tensor of dimension $n\times\cdots\times n$ with independent Bernoulli$(p)$ entries, where $k$ is fixed. For any $c,r>0$, we show that $\|T-\mathbb E T\|\le C_{k,r,c}\sqrt{np}$ with probability at least $1-n^{-r}$ whenever $np\ge c\log n$. We extend this bound to inhomogeneous Bernoulli sampling with deterministic entrywise weights. This removes the logarithmic factor in the work of Zhou and Zhu (2021). The proof follows the Kahn--Szemerédi light--heavy decomposition with a refined estimate on the heavy tuple part. We also obtain a log-free second eigenvalue bound for the random hypergraph model of Friedman and Wigderson (1995).

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-18 in stat.ML).
Categorie arXiv: Probability (math.PR) ; Combinatorics (math.CO); Statistics Theory (math.ST); Machine Learning (stat.ML).
Pagina del lavoro: https://arxiv.org/abs/2609.20520 — 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 2026-10-10T04:02:52.986Z dalla pagina https://arxiv.org/catchup/stat.ML/2026-09-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).