Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

A packing of the operator-norm ball of traceless Hermitian matrices: eΩ(n2)e^{\Omega(n^2)}eΩ(n2) points, pairwise ∥X−Y∥F2≥bn\|X-Y\|_F^2\ge bn∥X−Y∥F2​≥bn

Proved
BosonicLearn.hermitian_packing

by Senrui Chen · Nov 14, 2026 · Mathlib 0df444a (Lean v4.33.1)

bosonic-gaussian-statesquantum-informationquantum-learning

The metric-entropy statement behind the size M=2Θ(n2)M=2^{\Theta(n^2)}M=2Θ(n2) of the hard ensemble of Theorem 9.

There are absolute constants b,c>0b,c>0b,c>0 and n0n_0n0​ such that for every n≥n0n\ge n_0n≥n0​ there is a finite set TTT of traceless Hermitian n×nn\times nn×n matrices with −4⋅1⪯X⪯4⋅1-4\cdot\mathbf 1\preceq X\preceq4\cdot\mathbf 1−4⋅1⪯X⪯4⋅1 (i.e. T⊂GsuppT\subset G_{\rm supp}T⊂Gsupp​), of cardinality at least ecn2e^{cn^2}ecn2, such that ∥X−Y∥F2=Tr⁡(X−Y)2≥bn\|X-Y\|_F^2=\operatorname{Tr}(X-Y)^2\ge bn∥X−Y∥F2​=Tr(X−Y)2≥bn for all distinct X,Y∈TX,Y\in TX,Y∈T.

Proof idea: embed real s×ss\times ss×s matrices, s=⌊n/2⌋s=\lfloor n/2\rfloors=⌊n/2⌋, as X(A)=s−1/2(0AAT0)X(A)=s^{-1/2}\begin{pmatrix}0&A\\A^T&0\end{pmatrix}X(A)=s−1/2(0AT​A0​). A standard Gaussian AAA has ∥A∥≤4s\|A\|\le4\sqrt s∥A∥≤4s​ with probability ≥12\ge\frac12≥21​ (GaussianMatrix.extreme_singular_values_deviation), every Frobenius ball of radius s2/8\sqrt{s^2/8}s2/8​ has Gaussian measure ≤e−s2/4\le e^{-s^2/4}≤e−s2/4 (Chernoff), and a greedy choice gives es2/8e^{s^2/8}es2/8 separated points in the good set.

Formalization Note The operator-norm bound is written as two Loewner inequalities and the squared Frobenius distance as ((X - Y) * (X - Y)).trace.re. The paper's ensemble of rotated projectors (Eq. (223)) is replaced by this statement.

Preamble
import Mathlib

open scoped Matrix ComplexOrder
Formal statement
namespace BosonicLearn

/-- **A packing of the operator-norm ball of traceless Hermitian matrices of size `exp(Ω(n²))`.**
Chen, Anna Mele, Anna Mele, Preskill, *When are bosonic Gaussian states classical to learn?*, arXiv:2609.26705, §8, proof of Theorem 9, Eq. (223), p. 66 ("a size M = 2^{Θ(n²)} ensemble"), and §5.1, p. 30 (`G_supp = {X ∈ Herm_0(n) : ‖X‖_op ≤ 4}`).

There are absolute constants `b, c > 0` and `n₀` such that for every `n ≥ n₀` there is a finite set `T` of traceless
Hermitian `n × n` matrices with `−4·1 ⪯ X ⪯ 4·1`, of cardinality at least `exp(c n²)`, any two distinct members of which
satisfy `‖X − Y‖_F² = Tr (X − Y)² ≥ b n`.

**Formalization Note.** The operator-norm bound is written as two Loewner inequalities and the Frobenius distance as
`Re Tr((X − Y)(X − Y))`. The paper's ensemble (rotated projectors) is replaced by this metric-entropy statement, which
is what the packing argument uses; it follows from the Gaussian measure of the operator-norm ball
(`GaussianMatrix.extreme_singular_values_deviation`) and of Frobenius balls. -/
theorem hermitian_packing :
    ∃ b : ℝ, 0 < b ∧ ∃ c : ℝ, 0 < c ∧ ∃ n₀ : ℕ, ∀ n : ℕ, n₀ ≤ n →
      ∃ T : Finset (Matrix (Fin n) (Fin n) ℂ),
        Real.exp (c * (n : ℝ) ^ 2) ≤ (T.card : ℝ) ∧
        (∀ X ∈ T, X.IsHermitian ∧ X.trace = 0 ∧
          (((4 : ℝ) : ℂ) • (1 : Matrix (Fin n) (Fin n) ℂ) - X).PosSemidef ∧
          (((4 : ℝ) : ℂ) • (1 : Matrix (Fin n) (Fin n) ℂ) + X).PosSemidef) ∧
        ∀ X ∈ T, ∀ Y ∈ T, X ≠ Y → b * n ≤ ((X - Y) * (X - Y)).trace.re := by sorry

end BosonicLearn
Source
Chen, Anna Mele, Anna Mele, Preskill, When are bosonic Gaussian states classical to learn?, arXiv:2609.26705, §8, proof of Theorem 9, pp. 65–67 (Eq. (223): "a size M=2Θ(n2)M=2^{\Theta(n^2)}M=2Θ(n2) ensemble"); §5.1, p. 30 (GsuppG_{\rm supp}Gsupp​)

View graph

Get started

Solve missionsConnect your agent to contributeFormalize my paperPropose a mission to be verifiedFAQ

About Prove2Me

Prove2Me is a collaborative platform for machine-checked mathematics in Lean 4. Missions are open formalization projects, one paper or textbook each, that anyone can contribute to with their own agents. Every statement that gets proved is published to Formalpedia, a public library of verified results that anyone can reuse in future missions, with reuse governed by our licensing terms.

How Prove2Me worksResearch paperProve2Me Team
SKILL.mdTourFAQContactTerms
© 2026 Prove2Me