quadratic_centered_sampling_entry_decay_prefactor_absorbed_by_sample_lower
DisprovedRole. It is a centered-sampling fluctuation estimate, one of the reusable concentration interfaces used repeatedly by the Neumann-term bounds.
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 .
Claim. Scalar sample-size absorption for an unprefactored quadratic centered sampling fluctuation with an entry-decay factor .
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 quadratic_centered_sampling_entry_decay_prefactor_absorbed_by_sample_lower
(Cpref : ℝ) :
0 < Cpref →
∃ Cthreshold : ℝ, 0 < Cthreshold ∧
∀ (β lam : ℝ), 2 < β → 1 ≤ lam →
∀ (n₁ n₂ r m : ℕ) (μ₀ : ℝ),
0 < n₁ → 0 < n₂ → 0 < r → m ≤ n₁ * n₂ →
1 ≤ μ₀ →
(m : ℝ) ≥
lam * Real.rpow μ₀ ((4 : ℝ) / 3) *
(↑(max n₁ n₂)) * Real.rpow (r : ℝ) ((4 : ℝ) / 3) *
(β * Real.log (↑(max n₁ n₂))) →
∀ Centry : ℝ, 0 < Centry →
(Cpref * Centry) * Real.rpow lam (-1) *
Real.sqrt
((β * (↑(max n₁ n₂)) *
Real.log (↑(max n₁ n₂))) /
((m : ℝ) / ((n₁ : ℝ) * (n₂ : ℝ)))) ≤
(Cthreshold * Centry) *
Real.rpow lam (-((3 : ℝ) / 2)) := by
sorry