{
 "artifacts": null,
 "category": "architecture",
 "description": "Replace independently normalized attention or routing weights with an entropic doubly stochastic transport plan, while choosing its regularization ε using the paper's explicit statistical-stability bound. Increase ε when residual inversion or minibatch fluctuations are amplified, and decrease it only when the estimated bound permits sharper assignments.",
 "formulas_latex": [
  "$$d_{\\infty}([\\widehat{f}_{\\varepsilon,n}],[f_{\\varepsilon}])\\leq\\frac{CK_{0}}{\\sqrt{n}}\\left[A_{0}\\varepsilon^{1-r-p}\\sqrt{H_{\\varepsilon}}+E_{0}\\varepsilon^{1-r-a}\\sqrt{\\log(4/\\delta)}\\right].$$",
  "$$d_{\\infty}([u],[v])=\\inf_{b\\in\\mathbb R}\\|u-v-b\\|_{\\infty}=\\tfrac12\\operatorname{osc}(u-v).$$",
  "$$P_{ij}(\\varepsilon)=\\exp\\!\\left(\\frac{q_i^{\\top}k_j+\\alpha_i+\\beta_j}{\\varepsilon}\\right),\\qquad \\sum_jP_{ij}=r_i,\\quad \\sum_iP_{ij}=c_j.$$",
  "$$\\widehat B(\\varepsilon)=\\frac{\\widehat K(\\varepsilon)}{\\sqrt n}\\left[A_0\\varepsilon^{1-r-p}\\sqrt{\\widehat H_\\varepsilon}+E_0\\varepsilon^{1-r-a}\\sqrt{\\log(4/\\delta)}\\right],\\qquad \\varepsilon_{t+1}=\\operatorname{clip}\\bigl(\\varepsilon_t\\exp(-\\eta\\,\\operatorname{sign}(\\widehat B_t-\\tau)),\\varepsilon_{\\min},\\varepsilon_{\\max}\\bigr).$$"
 ],
 "id": 2812,
 "implementation": "Integrate this into the attention-logit or MoE-router path before the final weighted aggregation. For a minibatch of n tokens, compute scores Sij = qiᵀkj, define Kij = exp(Sij/ε), set row marginals ri = 1/n and column marginals cj = 1/m, and run 5–20 log-domain Sinkhorn iterations to obtain potentials α and β and transport weights P. Center every potential by subtracting its median to fix the quotient gauge. Maintain an exponential moving average of the observed Sinkhorn residual R = (P1−r, Pᵀ1−c). Estimate the local inverse-stability factor K-hat by finite differences: perturb the centered potentials or logits by small random vectors ξ, recompute the residual, and use K-hat = max ||ξ||∞ / ||ΔR||∞ over several probes, with damping and clipping. Estimate H-hatε from empirical variance or a simple covering proxy of normalized kernel rows; initially use a constant calibrated on a held-out batch. Fit exponents a, p, and r by regressing the envelope, complexity proxy, and K-hat against log ε over a temperature grid. Compute B-hat(ε) from the displayed bound and update ε toward a target noise budget τ. The first experiment should use CIFAR-10 or a small language model, comparing softmax attention, fixed-temperature Sinkhorn attention, and calibrated Sinkhorn attention at equal FLOPs. Measure validation loss, attention-plan variance, entropy, residual size, and loss spikes under small minibatches. Success means lower plan variance and equal-or-better validation loss without more Sinkhorn iterations.",
 "math_summary": "The paper's polynomial-stability principle states that if the summed entropy integral is bounded by A₀ ε^(-p) sqrt(Hε), the function-class envelope is bounded by E₀ ε^(-a), and the population Sinkhorn residual has inverse stability constant K₀ ε^(-r), then with probability at least 1−δ, the quotient sup-norm error is at most C K₀ / sqrt(n) times [A₀ ε^(1−r−p) sqrt(Hε) + E₀ ε^(1−r−a) sqrt(log(4/δ))]. Here n is the number of tokens or routing items, ε is the entropic temperature, Hε is the entropy-complexity term for normalized kernel sections, A₀, E₀, and C are scale constants, and a, p, and r describe envelope, complexity, and inverse-residual stability dependence on ε. The quotient metric d∞([u],[v]) = inf over b in R of ||u−v−b||∞ = one half of osc(u−v) removes the arbitrary additive gauge of Sinkhorn potentials. Use the bound as a temperature controller, with K₀ ε^(-r) estimated by the local inverse sensitivity of the Sinkhorn residual.",
 "math_tags": [
  "optimal-transport",
  "probability",
  "statistics",
  "convex-analysis"
 ],
 "ml_areas": [
  "attention",
  "moe-routing",
  "regularization"
 ],
 "paper": {
  "arxiv_id": "2608.29152",
  "arxiv_url": "https://arxiv.org/abs/2608.29152",
  "summary_what_math_gives_to_ml": "The paper isolates a useful decomposition for entropic transport estimation: empirical operator fluctuations scale as n^(-1/2), while inverse stability of the population Sinkhorn fixed point controls how strongly those fluctuations are amplified. The transferable asset is the explicit polynomial dependence on the entropic temperature ε, which can prevent neural transport modules from selecting an unnecessarily sharp and unstable temperature. A practical adaptation is a Sinkhorn attention or MoE router whose ε is adjusted using online estimates of residual sensitivity and minibatch complexity rather than treated as a fixed hyperparameter. This creates a falsifiable tradeoff between sharper assignments and routing noise.",
  "title": "Uniform Statistical Convergence of Empirical Sinkhorn Potentials with Exponential and Polynomial Dependence on the Regularization Parameter",
  "year": "2026"
 },
 "ratings": {
  "difficulty": 6,
  "novelty": 6,
  "usefulness": 6
 },
 "solves": [
  "stability",
  "accuracy",
  "sample-efficiency"
 ],
 "title": "Stability-calibrated Sinkhorn attention",
 "url": "https://synthcore.org/idea/2812/stability-calibrated-sinkhorn-attention",
 "verification": {
  "peer_reviewed": false,
  "status": "unverified",
  "status_label": "Unverified",
  "verdict_source": "deterministic test code (paired-seed permutation statistics)"
 }
}