prefactored_centered_sampling_linear_neumann_prefactor_bound_from_base_entry_scale
ProvedRole. It belongs to the golfing/Neumann-series certificate branch, where the certificate is decomposed into linear and quadratic sampling terms.
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. Raw fixed-matrix event step for a linear Neumann contribution with prefactor , leaving the base-entry scalar scale unabsorbed.
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. This node is currently a leaf problem in the decomposition tree, intended to be proved directly by later agents.
import Definitions.Def_matrix_completion_tangent open MatrixCompletion
theorem prefactored_centered_sampling_linear_neumann_prefactor_bound_from_base_entry_scale
(Cfixed Cbase : ℝ) :
0 < Cfixed → 0 < Cbase →
∃ Cpref : ℝ, 0 < Cpref ∧
∀ (β lam : ℝ), 2 < β → 1 ≤ lam →
∀ (n₁ n₂ r m : ℕ) (μ₀ μ₁ : ℝ),
0 < n₁ → 0 < n₂ → 0 < r → m ≤ n₁ * n₂ →
1 ≤ μ₀ → 1 ≤ μ₁ →
∀ (Omega : Finset (Fin n₁ × Fin n₂))
(B Y : Matrix (Fin n₁) (Fin n₂) ℝ),
Y =
(((m : ℝ) / ((n₁ : ℝ) * (n₂ : ℝ)))⁻¹ *
(1 - 2 * ((m : ℝ) / ((n₁ : ℝ) * (n₂ : ℝ))))) •
centeredSamplingFluctuation Omega
((m : ℝ) / ((n₁ : ℝ) * (n₂ : ℝ))) B →
entrySupNorm B ≤
Cbase * μ₁ *
Real.sqrt ((r : ℝ) / ((n₁ : ℝ) * (n₂ : ℝ))) *
(μ₀ * (r : ℝ) / (↑(max n₁ n₂))) →
CenteredSamplingSpectralBound Omega
((m : ℝ) / ((n₁ : ℝ) * (n₂ : ℝ))) B
(Cfixed * Real.sqrt
((β * (↑(max n₁ n₂)) *
Real.log (↑(max n₁ n₂))) /
((m : ℝ) / ((n₁ : ℝ) * (n₂ : ℝ)))) *
entrySupNorm B) →
spectralNorm Y ≤
Cpref * Cbase *
|(((m : ℝ) / ((n₁ : ℝ) * (n₂ : ℝ)))⁻¹) *
(1 - 2 * ((m : ℝ) / ((n₁ : ℝ) * (n₂ : ℝ))))| *
μ₁ * Real.sqrt ((r : ℝ) / ((n₁ : ℝ) * (n₂ : ℝ))) *
(μ₀ * (r : ℝ) / (↑(max n₁ n₂))) *
Real.sqrt
((β * (↑(max n₁ n₂)) *
Real.log (↑(max n₁ n₂))) /
((m : ℝ) / ((n₁ : ℝ) * (n₂ : ℝ)))) := by
sorry