Metraipolis › archive › dc_0bb070c4539d

FlashCart: Fast Cartesian Tensor Products for Equivariant Interatomic Potentials — arXiv:2610.06409

Source
arXiv
Original
https://arxiv.org/abs/2610.06409
License (as archived)
CC0-1.0
Archived
2026-10-06T05:31:37.884Z
SHA-256 of the archived text
88e14cacbf42894d210e2a1b36a796371f6f71e0304f83bc023b2e4b73fd51c7
Stable URL of this page
https://metraipolis.com/documento/dc_0bb070c4539d

How to cite

FlashCart: Fast Cartesian Tensor Products for Equivariant Interatomic Potentials — arXiv:2610.06409 — arXiv, https://arxiv.org/abs/2610.06409 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0bb070c4539d (Metraipolis archive dc_0bb070c4539d, sha256 88e14cacbf42894d210e2a1b36a796371f6f71e0304f83bc023b2e4b73fd51c7)
BibTeX
@misc{dc0bb070c4539d,
  title = {FlashCart: Fast Cartesian Tensor Products for Equivariant Interatomic Potentials — arXiv:2610.06409},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.06409},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0bb070c4539d; sha256 88e14cacbf42894d210e2a1b36a796371f6f71e0304f83bc023b2e4b73fd51c7},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.06409. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Machine-learned interatomic potentials extend atomistic simulations beyond the length- and timescales accessible to electronic-structure methods. However, the computational cost of equivariant architectures limits the local correlations they can represent in practice and therefore their achievable accuracy. Here we introduce FlashCart, which makes higher-order correlations affordable by combining generated GPU kernels with an architecture that recursively builds equivariant features and compresses them to a fixed width at each step. We express tensor products in independent Cartesian components and symbolically simplify them and their derivatives, producing fused kernels that often outperform optimized spherical counterparts. We then show that increasing correlation order improves accuracy more efficiently than increasing width, depth, or tensor rank. On SPICE-MACE-OFF, FlashCart models advance the measured accuracy-efficiency frontier: a model with $5.6$ million parameters achieves lower energy and force errors and $10\times$ faster inference than a transformer with $189$ million parameters.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.06409 — 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 2026-10-06T05:27:05.884Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).