OnlineLearning.separating_functional_ne_zero
theoremverifiedimported Lean
A nonzero separating functional over the upper image. Let $X, Y \subseteq \bbr$, let $f : \bbr \to \bbr \to \bbr$ be a payoff, and let $u$ be a finite sample of columns drawn from $Y$, with $X$ nonempty. Fix a vector $c : u \to \bbr$ and a continuous linear functional $L : (u \to \bbr) \to \bbr$. If $L(z) < L(c)$ for every $z$ in the finite upper image $U(X,f,u)$, then $L$ is not the zero functional.
Statement
set_option relaxedAutoImplicit false in set_option autoImplicit false in open Real Finset BigOperators in lemma OnlineLearning.separating_functional_ne_zero {X Y : Set ℝ} {f : ℝ → ℝ → ℝ} {u : Finset Y} {cvec : u → ℝ} (hX : X.Nonempty) (L : (u → ℝ) →L[ℝ] ℝ) (hsep : ∀ z ∈ finiteUpperImage X f u, L z < L cvec) : L ≠ 0
- Source
- TCSlib, `OnlineLearning.separating_functional_ne_zero`
- Lean proof
- By Karim Abdel Sadek, Mark Bedaywi, from github.com/Shilun-Allan-Li/tcslib at
c8a02591b1e5(Copyright (c) 2026 Karim Abdel Sadek and Mark Bedaywi. All rights reserved, Apache-2.0). Compiled here against leanprover/lean4:v4.33.1, Mathlib v4.33.1; written for leanprover/lean4:v4.25.0.OnlineLearning.separating_functional_ne_zero← OnlineLearning.separating_functional_ne_zero (TCSlib/LearningTheory/Minimax/ConvexMinimaxSeparation.lean:217): verbatim
- Verified
- 07 Oct 2026
- Axioms
Classical.choiceQuot.soundpropext- Built on 2
- OnlineLearning.finiteUpperImageFor sets $X, Y \subseteq \bbr$, a payoff $f : \bbr \to \bbr \to \bbr$, and a finite sample $u$ of columns from $Y$, the finite upper image…
- OnlineLearning.finiteUpperImage_nonemptyNonemptiness of the finite upper image. Let $X, Y \subseteq \bbr$, let $f : \bbr \to \bbr \to \bbr$ be a payoff function, and let $u$ be a…
- Used by 1
- OnlineLearning.separating_weight_sum_posPositivity of the separator's total weight. Let $X, Y \subseteq \bbr$, let $f : \bbr \to \bbr \to \bbr$ be a payoff function, and let $u$…
Lean source view module on GitHub
Choose a tactic — a marked line — to see the goals Lean had before and after it, as in Lean’s infoview. Step with ← → or j k.
set_option relaxedAutoImplicit false inset_option autoImplicit false inopen Real Finset BigOperators in/-- A functional separating the (nonempty) upper image from a point is nonzero: the zero functional cannot be strictly smaller on every upper-image point than on `cvec`. -/lemma OnlineLearning.separating_functional_ne_zero {X Y : Set ℝ} {f : ℝ → ℝ → ℝ} {u : Finset Y} {cvec : u → ℝ} (hX : X.Nonempty) (L : (u → ℝ) →L[ℝ] ℝ) (hsep : ∀ z ∈ finiteUpperImage X f u, L z < L cvec) : L ≠ 0 := by intro hL rcases finiteUpperImage_nonempty (X := X) (Y := Y) (f := f) hX u with ⟨z, hz⟩ simpa [hL] using hsep z hz