{
  "abstract": "Hyper-connections widen the residual stream of a Transformer to $n$ parallel streams. Their manifold-constrained version (mHC) mixes the streams at each layer with a doubly stochastic matrix, which it computes by Sinkhorn normalization of exponentiated logits. We give a geometric theory of this design on the Birkhoff polytope. First, a doubly stochastic mixer splits the stream into a mean channel, on which mHC is exactly a residual network, and a difference channel, which each layer contracts by its second singular value $σ_2 \\le 1 - n \\min_{ij} H_{ij}$. Thus the extra width is a fading memory with a horizon of $1/(1-σ_2)$ layers, and among nonnegative mixers only the permutations do not collapse. Second, the Sinkhorn-logit map is a global chart, and its logit gradient is exactly the Fisher-Rao gradient. Thus logit gradient flow follows a squared Fisher-Rao metric, and the straight-through update is exactly entropic mirror descent. Third, under logit gradient flow the logarithm of each entry moves at a rate of at most $4n^3\\|\\nabla f\\|_\\infty \\varepsilon$, where $\\varepsilon$ is the distance to the nearest permutation. Thus gradient flow approaches and leaves the vertices only at rate $1/t$, but mirror descent moves at an exponential rate. Fourth, the local convergence factor of Sinkhorn is $σ_2^2$, so a fixed iteration budget limits the horizon. Experiments confirm the predicted rates.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2610.06653",
  "author_total": 3,
  "authors": [
    {
      "name": "Xiaoyu Li"
    },
    {
      "name": "Zhizhou Sha"
    },
    {
      "name": "Chiwun Yang"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/73hy1f7tfxgrj.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2610.06653",
  "fulltext_url": null,
  "id": "73hy1f7tfxgrj",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2610.06653",
  "language": null,
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "article",
  "licence_url": "http://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "cs.LG"
    ],
    [
      "arxiv",
      "math.OC"
    ],
    [
      "arxiv",
      "stat.ML"
    ],
    [
      "openalex",
      "1702|Stochastic Gradient Optimization Techniques"
    ]
  ],
  "openalex": "W7220651443",
  "pdf_url": "https://arxiv.org/pdf/2610.06653",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-05",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/73hy1f7tfxgrj.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:27:10Z",
      "native_id": "2610.06653",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2610.06653"
    }
  ],
  "subjects": [
    {
      "field": "mathematics",
      "origin": "arxiv:math.OC",
      "subfield": "optimisation-control"
    },
    {
      "field": "mathematics",
      "origin": "arxiv:stat.ML",
      "subfield": "statistics"
    }
  ],
  "title": "The Birkhoff Geometry of Manifold-Constrained Hyper-Connections: Two Channels, Vertex Viscosity, and Sinkhorn as a Retraction",
  "title_text": "The Birkhoff Geometry of Manifold-Constrained Hyper-Connections: Two Channels, Vertex Viscosity, and Sinkhorn as a Retraction",
  "type": "preprint",
  "updated_at": "2026-10-30T12:27:16Z",
  "url": "https://research.draconitic.com/paper/73hy1f7tfxgrj",
  "venue": "arXiv",
  "versions": []
}