A non-stationary start with gives
ProvedNonconvexSplitting.ProxADMM.x1_ne_x0admmnonconvex-optimizationp2o-batch-p200bp2o-gran-per-chapterp2o-plan-paperp2o-v1
Assume the standing assumptions and Assumption 1, and let be generated by the proximal ADMM. Suppose the initial point is not a stationary point of , that , and that satisfies . Then
This is the first step of the proof that a non-stationary start is strictly improved upon.
Preamble
import Mathlib import Definitions.Def_NonconvexSplitting_Shared_IsStationary import Definitions.Def_NonconvexSplitting_Shared_StandingAssumptions import Definitions.Def_NonconvexSplitting_Shared_IsProxADMMSeq import Definitions.Def_NonconvexSplitting_Shared_Assumption1 open NonconvexSplitting.Shared open Filter Topology open scoped InnerProductSpace
Formal statement
namespace NonconvexSplitting.ProxADMM
/-- Li–Pong, p. 10: from a non-stationary start with `M* z⁰ = ∇h(x⁰)`, the first primal step moves. -/
theorem x1_ne_x0 {n m : ℕ} (h : EuclideanSpace ℝ (Fin n) → ℝ) (P : EuclideanSpace ℝ (Fin m) → EReal)
(phi : EuclideanSpace ℝ (Fin n) → ℝ) (M : EuclideanSpace ℝ (Fin n) →L[ℝ] EuclideanSpace ℝ (Fin m)) (β : ℝ)
(hstd : StandingAssumptions h P phi β)
(σ δ γ : ℝ) (Q1 Q2 T1 T2 Q3 : EuclideanSpace ℝ (Fin n) →L[ℝ] EuclideanSpace ℝ (Fin n))
(hA : Assumption1 h phi M β σ Q1 Q2 T1 T2 δ Q3 γ)
(x : ℕ → EuclideanSpace ℝ (Fin n)) (y z : ℕ → EuclideanSpace ℝ (Fin m))
(hseq : IsProxADMMSeq h P phi M β x y z)
(hz0 : ContinuousLinearMap.adjoint M (z 0) = gradient h (x 0))
(hns : ¬ IsStationary h P M (x 0))
(hfin : ((h (x 0) : ℝ) : EReal) + P (M (x 0)) ≠ ⊤) :
x 1 ≠ x 0 := by sorry
end NonconvexSplitting.ProxADMM
Source
Li & Pong, Global Convergence of Splitting Methods for Nonconvex Composite Optimization, arXiv:1407.0753v6, p. 10, first paragraph of the proof of Theorem 1(ii)
Human review
Confirmed by the mission captain (proposal self-audit).
Confirmed by the moderator at approval.