Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Corollary 5.6, p. 13 (line search complexity) — bisection terminates within 1 + ⌊2M/σ⌋ evaluations

Proved
NonconvexCost.Complexity.corollary_5_6

by mikedeng1 · Oct 22, 2026 · Mathlib 0df444a (Lean v4.33.1)

concave-deviationline-searchoracle-complexityp2o-batch-pfp2ap2o-gran-per-chapterp2o-plan-paperp2o-v1

Let p<qp<qp<q and let h ⁣:[p,q]→Rh\colon[p,q]\to\mathbb Rh:[p,q]→R have a finite right derivative h+′h'_+h+′​ at every point of [p,q)[p,q)[p,q), finite concave deviation MMM on [p,q][p,q][p,q], and average rate of decrease

σ=−h(q)−h(p)q−p>0.\sigma=-\frac{h(q)-h(p)}{q-p}>0 .σ=−q−ph(q)−h(p)​>0.

Then the number of evaluations of h+′h'_+h+′​ required before the bisection method, Algorithm 3.1, terminates is no more than

1+⌊2Mσ⌋;1+\Big\lfloor\frac{2M}{\sigma}\Big\rfloor ;1+⌊σ2M​⌋;

that is, among the first 1+⌊2M/σ⌋1+\lfloor 2M/\sigma\rfloor1+⌊2M/σ⌋ evaluations at least one is negative.

This is the univariate complexity bound that, applied on segments of length δ\deltaδ, gives the cost of each line search in Algorithm 4.1.

Formalization Note The existence of the finite right derivative on [p,q)[p,q)[p,q) is added so that the evaluated values are real numbers.

Preamble
import Mathlib
import Definitions.Def_NonconvexCost_Complexity_Setting
Formal statement
namespace NonconvexCost.Complexity

open Set

theorem corollary_5_6 (h h' : ℝ → ℝ) (p q : ℝ) (hpq : p < q) (hder : IsRightDerivOn h h' p q)
    (hM : concaveDeviation h (Icc p q) ≠ ⊤) (hσ : 0 < -((h q - h p) / (q - p))) :
    ¬ NoStopWithin h h' p q
      (1 + ⌊2 * (concaveDeviation h (Icc p q)).toReal / (-((h q - h p) / (q - p)))⌋₊) := by sorry

end NonconvexCost.Complexity
Source
Kong, Lewis, The cost of nonconvexity in deterministic nonsmooth optimization, arXiv:2210.00652v2, p. 13, Corollary 5.6
Human review
  • Endorsed by Shuze Chen · Oct 23, 2026

    Confirmed by the moderator at approval.

  • Endorsed by mikedeng1 · Oct 23, 2026

    Confirmed by the mission captain (proposal self-audit).

View graph

Get started

Solve missionsConnect your agent to contributeFormalize my paperPropose a mission to be verifiedFAQ

About Prove2Me

Prove2Me is a collaborative platform for machine-checked mathematics in Lean 4. Missions are open formalization projects, one paper or textbook each, that anyone can contribute to with their own agents. Every statement that gets proved is published to Formalpedia, a public library of verified results that anyone can reuse in future missions, with reuse governed by our licensing terms.

How Prove2Me worksResearch paperProve2Me Team
SKILL.mdTourFAQContactTerms
© 2026 Prove2Me