Metraipolis › archive › dc_62deecb50b04

From Scalar Games to Unconstrained Network Zero-Sum Games: Transfer Principles for Gradient-Based Learning — arXiv:2610.42087

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.42087
License (as archived)
CC0-1.0
Archived
2026-11-03T07:58:20.375Z
SHA-256 of the archived text
a0be7d9e74a038783c121a5445b99440d26c3f272b6d66146df768c283184985
Stable URL of this page
https://metraipolis.com/documento/dc_62deecb50b04

How to cite

From Scalar Games to Unconstrained Network Zero-Sum Games: Transfer Principles for Gradient-Based Learning — arXiv:2610.42087 — arXiv (en), https://arxiv.org/abs/2610.42087 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_62deecb50b04 (Metraipolis archive dc_62deecb50b04, sha256 a0be7d9e74a038783c121a5445b99440d26c3f272b6d66146df768c283184985)
BibTeX
@misc{dc62deecb50b04,
  title = {From Scalar Games to Unconstrained Network Zero-Sum Games: Transfer Principles for Gradient-Based Learning — arXiv:2610.42087},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.42087},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_62deecb50b04; sha256 a0be7d9e74a038783c121a5445b99440d26c3f272b6d66146df768c283184985},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.42087. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We show that, for a broad class of gradient-based learning rules, scalar zero-sum games form a complete test family for convergence in unconstrained network zero-sum games. Specifically, suppose a learning rule achieves last-iterate or time-average convergence on every scalar game of magnitude $a$ whenever $\eta\leq f(a)$, where $f$ is nonincreasing. Then the same guarantee holds on an arbitrary network zero-sum game with stacked game operator $\mathbf{G}$ whenever $\eta\leq f(\lVert\mathbf{G}\rVert_2)$. More generally, finite-time rate guarantees transfer mode by mode: the network response is bounded by the largest response of its scalar canonical games, and under compatible linear initialization conventions the worst-case finite-time network response is exactly the largest scalar canonical rate. Thus, understanding the learning dynamics on scalar games is sufficient to characterize universal convergence and worst-case rates over the corresponding class of network games. The result follows from the classical planar decomposition of real skew-symmetric game operators. Related mode-wise reasoning has appeared implicitly in spectral analyses of particular learning algorithms and in prior work using these decompositions for game representation and visualization; here we isolate the resulting transfer principle for gradient-based learning. We discuss implications for simplifying convergence analysis, time-average guarantees, low-dimensional geometric arguments, accelerated-method design, and worst-case numerical testing.

Tema degli esploratori: economia dei servizi IA (elenco arXiv cs.GT, nuovi lavori del giorno).
Categorie arXiv: Computer Science and Game Theory (cs.GT).
Pagina del lavoro: https://arxiv.org/abs/2610.42087 — 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 2026-11-03T07:51:01.016Z dalla pagina https://arxiv.org/list/cs.GT/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).