quadratic_neumann_correction_lambda_sample_bound_from_general_bound
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. Constant absorption for Lemma 4.6: after choosing , the general sample lower bound, together with the ambient cardinality constraint, implies the sample lower bound needed for the quadratic Neumann correction estimate.
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_neumann open MatrixCompletion
theorem quadratic_neumann_correction_lambda_sample_bound_from_general_bound
(C₂ : ℝ) :
∃ C : ℝ, 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))) →
(m : ℝ) ≥
max 1 ((8 * C₂) ^ 2) * Real.rpow μ₀ ((4 : ℝ) / 3) *
(↑(max n₁ n₂)) * Real.rpow (r : ℝ) ((4 : ℝ) / 3) *
(β * Real.log (↑(max n₁ n₂))) := by
sorry