Metraipolis › archive › dc_371933f4ea8b

Sharp Restricted Isometry Thresholds for Global Minima of Rank-Restricted Matrix LASSO — arXiv:2608.29018

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.29018
License (as archived)
CC0-1.0
Archived
2026-10-17T08:39:49.137Z
SHA-256 of the archived text
4d9cfe1165b807972ae19186b8bcf75d33c3ab8194d208c311bbd344a47ccb80
Stable URL of this page
https://metraipolis.com/documento/dc_371933f4ea8b

How to cite

Sharp Restricted Isometry Thresholds for Global Minima of Rank-Restricted Matrix LASSO — arXiv:2608.29018 — arXiv (en), https://arxiv.org/abs/2608.29018 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_371933f4ea8b (Metraipolis archive dc_371933f4ea8b, sha256 4d9cfe1165b807972ae19186b8bcf75d33c3ab8194d208c311bbd344a47ccb80)
BibTeX
@misc{dc371933f4ea8b,
  title = {Sharp Restricted Isometry Thresholds for Global Minima of Rank-Restricted Matrix LASSO — arXiv:2608.29018},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.29018},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_371933f4ea8b; sha256 4d9cfe1165b807972ae19186b8bcf75d33c3ab8194d208c311bbd344a47ccb80},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.29018. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We determine the sharp restricted isometry threshold for recovery at global minima of the rank-restricted matrix LASSO. For target rank $r_{\star}$, if the rank-$k$ RIP constant satisfies $\delta<\delta_{\mathrm{sharp}}(k/r_{\star})$, where $\delta_{\mathrm{sharp}}(t)=t/(4-t)$ for $0<t<4/3$ and $\delta_{\mathrm{sharp}}(t)=\sqrt{(t-1)/t}$ for $t\ge4/3$, then every global minimizer has Frobenius error $\lesssim\sqrt{r_{\star}}\lambda$ for all $\lambda\gtrsim\|\mathcal{A}^{*}(\xi)\|_{\mathrm{op}}$ and at every search rank $r\ge r_{\star}$. The constants depend only on the RIP constant and $t=k/r_{\star}$, and in particular are independent of the search rank. When the rank restriction is inactive, the result specializes to the ordinary convex matrix LASSO. We also obtain the analogous results for sparsity-restricted vector LASSO. Conversely, we show that the threshold $\delta<\delta_{\mathrm{sharp}}(k/r_{\star})$ cannot be improved, due to the existence of counterexamples whose global minimizers fail to recover the ground truth.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-01 in cs.LG).
Categorie arXiv: Machine Learning (stat.ML) ; Information Theory (cs.IT); Machine Learning (cs.LG); Optimization and Control (math.OC); Statistics Theory (math.ST).
Pagina del lavoro: https://arxiv.org/abs/2608.29018 — 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 2026-10-17T08:13:26.896Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).