Metraipolis › archive › dc_424ab1df8ea1

Gaussian Partitioning for Reliable Learning of Multi-Index Models — arXiv:2611.05264

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.05264
License (as archived)
CC0-1.0
Archived
2026-11-04T21:53:35.325Z
SHA-256 of the archived text
de13713814a495026bf36455203bcf0677b1b22e5ca3412ee46e25119918c50e
Stable URL of this page
https://metraipolis.com/documento/dc_424ab1df8ea1

How to cite

Gaussian Partitioning for Reliable Learning of Multi-Index Models — arXiv:2611.05264 — arXiv (en), https://arxiv.org/abs/2611.05264 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_424ab1df8ea1 (Metraipolis archive dc_424ab1df8ea1, sha256 de13713814a495026bf36455203bcf0677b1b22e5ca3412ee46e25119918c50e)
BibTeX
@misc{dc424ab1df8ea1,
  title = {Gaussian Partitioning for Reliable Learning of Multi-Index Models — arXiv:2611.05264},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.05264},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_424ab1df8ea1; sha256 de13713814a495026bf36455203bcf0677b1b22e5ca3412ee46e25119918c50e},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.05264. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We introduce Gaussian partitioning, an algorithmic primitive for distributions smooth with respect to a Gaussian. It partitions space into polyhedral regions so that almost all mass lies in thin strips restricting a few orthogonal directions. Within each strip, the conditional distribution approximately matches low-degree Gaussian moments in the unrestricted directions. Our construction builds on logconcave partitioning of Diakonikolas, Kane, and Ma (FOCS 2026). Under input marginals smooth with respect to the standard Gaussian, we obtain agnostic learners with error $(1+c)\mathrm{opt}+\epsilon$ for broad classes of Boolean multi-index models, including functions of halfspaces, low-dimensional convex concepts, and low-dimensional polynomial threshold functions. For functions of $k$ halfspaces, both agnostic and testable agnostic learners achieve this error with dimension dependence $d^{\mathrm{poly}(k/c)}$, improving the previous exponential dependence on $k/c$ in the agnostic exponent. For learning from positive examples with imperfect unlabeled data (PUI), we give algorithms and Statistical Query (SQ) lower bounds that qualitatively characterize complexity through Gaussian moment matching. For fixed smoothness and positive-mass parameters, we learn intersections of $k$ halfspaces with dimension dependence $d^{O(\log(k/\epsilon))}$ and matching SQ lower bounds, improving the previous $d^{\mathrm{poly}(1/\epsilon)}$ upper bound even for one halfspace. A general reduction from agnostic reliable learning to PUI yields negative reliable learners for these intersections with the same dimension dependence, for fixed smoothness. Finally, for PQ learning and testable learning with distribution shift, we prove qualitatively optimal SQ lower bounds of $d^{\Omega(1/\epsilon^2)}$, even for intersections of two halfspaces with Gaussian training data and arbitrary test distributions.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Data Structures and Algorithms (cs.DS) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2611.05264 — 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 2026-11-04T21:38:49.838Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).