nuclear_norm_lower_bound_by_tangent_sign_and_normal_norm
ProvedRole. It is part of the deterministic convex-optimization argument linking injectivity and dual certificates to exact 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 tangent-space nodes, the main event is that the sampled tangent operator is well conditioned; this prevents a nonzero tangent perturbation from agreeing with M on the sampled entries.
Claim. Subgradient lower bound for the nuclear norm at : the tangent component is paired with the sign matrix and the normal component contributes through its nuclear norm.
Lecture-note formulation:
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 nuclear_norm_lower_bound_by_tangent_sign_and_normal_norm
{n₁ n₂ r : ℕ} {M : Matrix (Fin n₁) (Fin n₂) ℝ}
(S : SVD M r) (H : Matrix (Fin n₁) (Fin n₂) ℝ) :
nuclearNorm M +
matrixInner (signMatrix S) (tangentProjection S H) +
nuclearNorm (normalProjection S H) ≤
nuclearNorm (M + H) := by
sorry