Metraipolis › archive › dc_4b526010cf34

Refined Topology-Pass Scheduling: Damped Trust-Region Compensation for Dynamic k-NN Graphs in SE(3)-Equivariant Structure Prediction — arXiv:2610.19246

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.19246
License (as archived)
CC0-1.0
Archived
2026-10-15T14:15:20.230Z
SHA-256 of the archived text
7e0f922607d3b2b765c9c31c190e9ddda2bd20a341ae1a6bd0840f7887352a32
Stable URL of this page
https://metraipolis.com/documento/dc_4b526010cf34

How to cite

Refined Topology-Pass Scheduling: Damped Trust-Region Compensation for Dynamic k-NN Graphs in SE(3)-Equivariant Structure Prediction — arXiv:2610.19246 — arXiv (en), https://arxiv.org/abs/2610.19246 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4b526010cf34 (Metraipolis archive dc_4b526010cf34, sha256 7e0f922607d3b2b765c9c31c190e9ddda2bd20a341ae1a6bd0840f7887352a32)
BibTeX
@misc{dc4b526010cf34,
  title = {Refined Topology-Pass Scheduling: Damped Trust-Region Compensation for Dynamic k-NN Graphs in SE(3)-Equivariant Structure Prediction — arXiv:2610.19246},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.19246},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4b526010cf34; sha256 7e0f922607d3b2b765c9c31c190e9ddda2bd20a341ae1a6bd0840f7887352a32},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.19246. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Equivariant structure-prediction pipelines alternate coordinate updates with the construction of a k-nearest-neighbour (kNN) graph whose membership is a discrete, piecewise-constant function of the coordinates. Rebuilding that graph at every block boundary (PB) is the expensive part of an epoch, whereas reusing one frozen graph (F) is fast but leaves a topology gap. We study a two-pass design in which the cheap pass records a small amount of state (margins, kNN radii, measured per-boundary displacements) and a second pass compensates conservatively. We formulate the choice of the graph-construction basis as a damped fixed-point iteration whose unique fixed point is exactly PB, and derive (i) exact non-flip certificates with the two-sided constant $m_i/4$ and one-sided constant $m_i/2$, (ii) the minimum-variance (BLUE) replay gain $\gamma^*$ and the resulting feasibility crossover, (iii) an $\ell_\infty$ trust-region projection that preserves convergence, and (iv) an analytic near-tie spacing law $E[m] \approx r_k/(3k)$ that matches measurements to 1\%. Three compensation levels are implemented in C++ (L1: frozen set with live geometry; L2: margin-gated local repair; L3: damped, projected basis) and validated under a matched-conditions protocol (identical seed, MSA depth and trajectory family, only the topology mode differs). L2 reproduces the PB edge set exactly ($D = 0.0000$ at every boundary), L1 stays within 0.6% and L3 interpolates monotonically: L2 reproduces the PB edge set exactly when the trust region is removed, and L3 interpolates between the frozen and the PB topology. The recorded trajectory itself yields a measured $1.5\times$ Pass-1 and $1.76\times$ epoch speed-up with no measurable loss gap. An open-source implementation of the runtime and of all the experiments reported here is available at this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.19246 — 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 2026-10-15T13:53:35.552Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).