bernoulli_least_squares_certificate_normal_bound_under_general_sample_bound
ProvedRole. It belongs to the dual-certificate branch, controlling the certificate that proves uniqueness of nuclear-norm recovery.
Problem and notation. Exact matrix completion asks when an unknown low-rank real matrix can be recovered from a random subset of its entries. Here has rank , entries are observed, and . Recovery means nuclear-norm minimization: minimize among matrices agreeing with on the observed entries. Probability notation. is the fixed-cardinality success probability: is chosen uniformly among all subsets of entries with , and the event is that the convex program uniquely returns . In Bernoulli nodes, or means each entry is sampled independently with probability , usually . Coherence notation. The object records SVD/singular-vector data for . The hypotheses and are the Candes-Recht incoherence assumptions: measures how spread out the singular vector spaces are, and measures the largest entry of the sign matrix . The parameter controls polynomial failure probabilities such as . For certificate nodes, is the tangent space at , and are the tangent and normal projections, and keeps only observed entries. The Neumann-series estimates control the dual certificate used to prove uniqueness of nuclear-norm recovery.
Claim. Under the general Candes-Recht sample lower bound, every least-squares certificate has normal component of spectral norm < 1 with high probability. This is the theorem-regime form of the Neumann-series estimates from Section 4.3.
Lecture-note formulation:
The constants in this node are universal existential constants; the theorem asserts that some positive constants with these roles exist.
Decomposition status. A corresponding proof sketch reduces this node to smaller mathematical subclaims. The checked reduction uses 6 subclaims: sampled sign matrix Neumann term small under general sample bound; linear Neumann correction small under general sample bound; quadratic Neumann correction small under general sample bound; Neumann certificate remainder small under general sample bound; least squares certificate normal bound from Neumann term bounds; sample ratio between zero and one.
import Definitions.Def_matrix_completion_tangent open MatrixCompletion
theorem bernoulli_least_squares_certificate_normal_bound_under_general_sample_bound :
∃ C c : ℝ, 0 < C ∧ 0 < c ∧
∀ C' : ℝ, C ≤ C' →
∀ (β : ℝ), 2 < β →
∀ (n₁ n₂ r m : ℕ) (M : Matrix (Fin n₁) (Fin n₂) ℝ)
(μ₀ μ₁ : ℝ) (S : SVD M r),
0 < n₁ → 0 < n₂ → 0 < r → m ≤ n₁ * n₂ →
1 ≤ μ₀ → 1 ≤ μ₁ →
A0 S μ₀ → A1 S μ₁ →
(m : ℝ) ≥
C' * max (max (μ₁ ^ 2) (Real.sqrt μ₀ * μ₁))
(μ₀ * Real.rpow (↑(max n₁ n₂)) ((1 : ℝ) / 4))
* (↑(max n₁ n₂)) * (r : ℝ) * (β * Real.log (↑(max n₁ n₂))) →
bernoulliEventProb ((m : ℝ) / ((n₁ : ℝ) * (n₂ : ℝ)))
(fun Omega =>
∀ Y : Matrix (Fin n₁) (Fin n₂) ℝ,
LeastSquaresDualCertificate Omega S Y →
spectralNorm (normalProjection S Y) < 1) ≥
1 - c * Real.rpow (↑(max n₁ n₂)) (-β) := by
sorry