Exact Moments of Gaussian Gram Hafnians Reveal an $n^2/\log n$ Threshold for Weak Anticoncentration

• URL: http://arxiv.org/abs/2608.17065v1
• Date: Mon, 17 Aug 2026 19:12:22 GMT
• Title: Exact Moments of Gaussian Gram Hafnians Reveal an $n^2/\log n$ Threshold for Weak Anticoncentration
• Abstract summary: Anticoncentration is central to hardness arguments for approximate sampling.<n> finite dimensional Haar moment transfer and high probability small ball anticoncentration remain separate problems.
• Score: 2.8224889996383395
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Anticoncentration is central to hardness arguments for approximate sampling. In the independent Gaussian surrogate for collision free Gaussian boson sampling, the moment ratio studied here also determines the averaged ideal linear cross entropy reference value. Let $H_{k,n}=\mathrm{haf}(X^{\mathsf T}X)$, where $X\in\mathbb{C}^{k\times 2n}$ has independent standard circular complex Gaussian entries. We evaluate $\mathbb{E}|H_{k,n}|^2$ and $\mathbb{E}|H_{k,n}|^4$ exactly by reducing four hafnian copies to a rank two Gaussian integral. For $R_{k,n}=(\mathbb{E}|H_{k,n}|^2)^2/\mathbb{E}|H_{k,n}|^4$, we obtain $R_{k,n}=4^{-n}\binom{2n}{n}/F_{k,n}$, where $F_{k,n}={}3F_2(-n,-n,1/2;1,k/2;1)$ is a terminating generalized hypergeometric polynomial. If $k/n^2\to c>0$, then $F{k,n}\to e^{1/c}I_0(1/c)$, where $I_0$ is the modified Bessel function of the first kind of order zero, and consequently $R_{k,n}\sqrt{πn}\to[e^{1/c}I_0(1/c)]^{-1}$. Thus $k\asymp n^2$ is a smooth Bessel crossover, whereas the scaling order boundary for inverse polynomial weak anticoncentration is $k\asymp n^2/\log n$. These conclusions concern the Gaussian surrogate moment criterion; finite dimensional Haar moment transfer and high probability small ball anticoncentration remain separate problems.

Related papers

• Zero-SNR Analyticity of the Scalar MMSE Is Equivalent to Gaussianity [0.7499255435598924]
  We prove that the minimum mean-square error $operatornamemmse_X(s)$ is analytic at zero signal-to-noise ratio if and only if $X$ is Gaussian.<n>A zero of $mgeq 2$ splits according to the roots of a Hermitemath and instead contributes a prefactor $n-m/2er_msqrt2n$.
  arXiv  Detail & Related papers  (2026-09-14T05:07:20Z)
• Permanents of matrix ensembles: computation, distribution, and geometry [0.0]
  We use the GPU to greaatly accelerate the computation of permanents over $mathbbC,$ $mathbbR,$ $mathbbF_p$ and $mathbbQ.$<n>We study the permanent along geodesics on the unitary group.<n>For the geodesic from the identity to the $n$-cycle permutation matrix, we find a universal scaling function $f(t)=frac1nln|perm((t))|$ that is independent of$n$ in
  arXiv  Detail & Related papers  (2026-02-08T22:31:42Z)
• Information-Computation Tradeoffs for Noiseless Linear Regression with Oblivious Contamination [65.37519531362157]
  We show that any efficient Statistical Query algorithm for this task requires VSTAT complexity at least $tildeOmega(d1/2/alpha2)$.
  arXiv  Detail & Related papers  (2025-10-12T15:42:44Z)
• Provably learning a multi-head attention layer [55.2904547651831]
  Multi-head attention layer is one of the key components of the transformer architecture that sets it apart from traditional feed-forward models. In this work, we initiate the study of provably learning a multi-head attention layer from random examples. We prove computational lower bounds showing that in the worst case, exponential dependence on $m$ is unavoidable.
  arXiv  Detail & Related papers  (2024-02-06T15:39:09Z)
• A Unified Framework for Uniform Signal Recovery in Nonlinear Generative Compressed Sensing [68.80803866919123]
  Under nonlinear measurements, most prior results are non-uniform, i.e., they hold with high probability for a fixed $mathbfx*$ rather than for all $mathbfx*$ simultaneously. Our framework accommodates GCS with 1-bit/uniformly quantized observations and single index models as canonical examples. We also develop a concentration inequality that produces tighter bounds for product processes whose index sets have low metric entropy.
  arXiv  Detail & Related papers  (2023-09-25T17:54:19Z)
• Classical shadows of fermions with particle number symmetry [0.0]
  We provide an estimator for any $k$-RDM with $mathcalO(k2eta)$ classical complexity. Our method, in the worst-case of half-filling, still provides a factor of $4k$ advantage in sample complexity.
  arXiv  Detail & Related papers  (2022-08-18T17:11:12Z)
• Learning a Single Neuron with Adversarial Label Noise via Gradient Descent [50.659479930171585]
  We study a function of the form $mathbfxmapstosigma(mathbfwcdotmathbfx)$ for monotone activations. The goal of the learner is to output a hypothesis vector $mathbfw$ that $F(mathbbw)=C, epsilon$ with high probability.
  arXiv  Detail & Related papers  (2022-06-17T17:55:43Z)
• Low-degree learning and the metric entropy of polynomials [44.99833362998488]
  We prove that any (deterministic or randomized) algorithm which learns $mathscrF_nd$ with $L$-accuracy $varepsilon$ requires at least $Omega(sqrtvarepsilon)2dlog n leq log mathsfM(mathscrF_n,d,|cdot|_L,varepsilon) satisfies the two-sided estimate $$c (1-varepsilon)2dlog
  arXiv  Detail & Related papers  (2022-03-17T23:52:08Z)
• Random matrices in service of ML footprint: ternary random features with no performance loss [55.30329197651178]
  We show that the eigenspectrum of $bf K$ is independent of the distribution of the i.i.d. entries of $bf w$. We propose a novel random technique, called Ternary Random Feature (TRF) The computation of the proposed random features requires no multiplication and a factor of $b$ less bits for storage compared to classical random features.
  arXiv  Detail & Related papers  (2021-10-05T09:33:49Z)
• Kernel Thinning [26.25415159542831]
  kernel thinning is a new procedure for compressing a distribution $mathbbP$ more effectively than i.i.d. sampling or standard thinning. We derive explicit non-asymptotic maximum mean discrepancy bounds for Gaussian, Mat'ern, and B-spline kernels.
  arXiv  Detail & Related papers  (2021-05-12T17:56:42Z)
• Near-Optimal SQ Lower Bounds for Agnostically Learning Halfspaces and ReLUs under Gaussian Marginals [49.60752558064027]
  We study the fundamental problems of agnostically learning halfspaces and ReLUs under Gaussian marginals. Our lower bounds provide strong evidence that current upper bounds for these tasks are essentially best possible.
  arXiv  Detail & Related papers  (2020-06-29T17:10:10Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.