Metraipolis › archive › dc_0807449b312e

Learning Gradients of Homogeneous Functions — arXiv:2611.01530

Source: arXiv (en)
Original: https://arxiv.org/abs/2611.01530
License (as archived): CC0-1.0
Archived: 2026-11-03T18:36:55.762Z
SHA-256 of the archived text: 7657e8f6e0050582581767f0019c272e97abb2213af2d6862a020cd902d1226b
Stable URL of this page: https://metraipolis.com/documento/dc_0807449b312e

How to cite

Learning Gradients of Homogeneous Functions — arXiv:2611.01530 — arXiv (en), https://arxiv.org/abs/2611.01530 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0807449b312e (Metraipolis archive dc_0807449b312e, sha256 7657e8f6e0050582581767f0019c272e97abb2213af2d6862a020cd902d1226b)

BibTeX

@misc{dc0807449b312e,
  title = {Learning Gradients of Homogeneous Functions — arXiv:2611.01530},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.01530},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0807449b312e; sha256 7657e8f6e0050582581767f0019c272e97abb2213af2d6862a020cd902d1226b},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.01530. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Homogeneous gradient functions have widespread significance, including applications in maximum energy subspace selection and retrieval problems. Euler's homogeneous function theorem specifies how the potential associated with a positively k-homogeneous gradient field can be recovered directly from the field itself. We use Euler's theorem to build on GradNets and propose a homogeneous gradient network architecture that is guaranteed to correspond to the gradient of a homogeneous function. Then, we describe how monotone homogeneous GradNets universally approximate the gradients of k-homogeneous convex functions. The inductive bias of homogeneous GradNets enables them to outperform baseline ICNNs by up to 7dB in our max energy subspace projection experiment and by up to 13% higher accuracy, 98% fewer parameters, and 70% fewer FLOPS in our amortized inner product search experiment.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Signal Processing (eess.SP); Optimization and Control (math.OC).
Pagina del lavoro: https://arxiv.org/abs/2611.01530 — 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 2026-11-03T18:12:54.507Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).