Metraipolis › archive › dc_8d658b05020d
Beyond Multi-Index Models: Learning Intersections of Degree-2 PTFs — arXiv:2611.05114
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.05114
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-04T12:41:06.271Z
- SHA-256 of the archived text
03bca59fecd488b7cdca891f4c6797abae0ddc1b85638853a185182605f59c57- Stable URL of this page
https://metraipolis.com/documento/dc_8d658b05020d
How to cite
Beyond Multi-Index Models: Learning Intersections of Degree-2 PTFs — arXiv:2611.05114 — arXiv (en), https://arxiv.org/abs/2611.05114 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_8d658b05020d (Metraipolis archive dc_8d658b05020d, sha256 03bca59fecd488b7cdca891f4c6797abae0ddc1b85638853a185182605f59c57)
BibTeX
@misc{dc8d658b05020d,
title = {Beyond Multi-Index Models: Learning Intersections of Degree-2 PTFs — arXiv:2611.05114},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.05114},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_8d658b05020d; sha256 03bca59fecd488b7cdca891f4c6797abae0ddc1b85638853a185182605f59c57},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.05114. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
We give an algorithm for PAC learning intersections of $k$ degree-2 polynomial threshold functions over $R^d$ under a Gaussian distribution. Our algorithm achieves classification error $\epsilon$ using $d^{O(k)}2^{O_k(\log^3(1/\epsilon))}$ time and samples, improving over the $d^{O(k^2/\epsilon^2)}$ running time of the polynomial regression approach. To our knowledge, our result is the first to obtain a dimension exponent independent of the accuracy parameter, even for $k=2$. We complement our algorithmic result with an SQ lower bound showing that the complexity dependence of $d^{\Omega(k)}$ is unavoidable. Lifting the input to polynomial features turns the target into an intersection of $k$ halfspaces. This suggests using the first two labeled moments for subspace recovery. In the lifted space, however, these moments can reveal nothing. Our starting point is a Gaussian comparison theorem showing that, for sufficiently regular defining quadratics, the labeled moments needed for subspace recovery are approximately preserved. To handle arbitrary defining quadratics, we establish a new structural result showing that every direction with significant resampling influence can be detected through degree-$O(k)$ moments. These results yield an initial $d^{O(k)}2^{\mathrm{poly}_k(1/\epsilon)}$-time learner using adaptive restrictions. To improve the exponential dependence on $1/\epsilon$, we develop a two-stage dimension-reduction approach that avoids the costly adaptive partitioning. After identifying a subspace containing all directions with large influence, we use generalized regularity and Gaussian comparison to recover the remaining relevant quadratic features through a new derivative-based moment operator. The recovered features support an intersection close to the target. Combining them with robust hinge-loss minimization gives our quasipolynomial-time learner.
Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Data Structures and Algorithms (cs.DS); Statistics Theory (math.ST); Machine Learning (stat.ML).
Pagina del lavoro: https://arxiv.org/abs/2611.05114 — 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 2026-11-04T12:29:47.325Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).