(2.21) — Ψ(x^md_k) − [(1−α_k)Ψ(x^ag_{k−1}) + α_kΨ(x)] ≤ α_k⟨∇Ψ(x^md_k), x_{k−1} − x⟩
ProvedNonconvexAG.Smooth.eq_2_21accelerated-gradientnonconvex-optimizationp2o-batch-pfp2bp2o-gran-per-chapterp2o-plan-paperp2o-v1
Let be convex and differentiable with -Lipschitz gradient, , and let be generated by Algorithm 1 from with step sizes , (), , . Then for every and every ,
This is where convexity enters the proof of Theorem 1 b).
Formalization Note The statement is the outer ends of the chain (2.21); convexity is ConvexOn ℝ Set.univ Ψ, and the inner product is the Euclidean one.
Preamble
import Mathlib import Definitions.Def_ConvexOptAlg_SmoothGD_Defs import Definitions.Def_NonconvexAG_Smooth_AGRun
Formal statement
namespace NonconvexAG.Smooth
/-- (2.21), p. 7 (outer ends of the chain), for convex `Ψ` and every `x ∈ ℝⁿ`. -/
theorem eq_2_21 {n : ℕ} (Ψ : E n → ℝ) (g : E n → E n) (LΨ : ℝ)
(hΨ : ConvexOptAlg.SmoothGD.IsBetaSmooth Ψ g LΨ) (hL : 0 < LΨ)
(α β lam : ℕ → ℝ) (hstep : AGStepsizes α β lam) (x0 : E n) (hconv : ConvexOn ℝ Set.univ Ψ) :
∀ k, 1 ≤ k → ∀ x : E n,
Ψ (xmdSeq g α β lam x0 k) - ((1 - α k) * Ψ (xagSeq g α β lam x0 (k - 1)) + α k * Ψ x) ≤
α k * inner ℝ (g (xmdSeq g α β lam x0 k)) (xSeq g α β lam x0 (k - 1) - x) := by sorry
end NonconvexAG.Smooth
Source
Ghadimi & Lan, Accelerated Gradient Methods for Nonconvex Nonlinear and Stochastic Programming, arXiv:1310.3787v1, p. 7, (2.21)
Human review
Confirmed by the mission captain (proposal self-audit).
Confirmed by the moderator at approval.