OnlineLearning.finiteUpperImage
defimported Lean
For 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 is the set \[ U(X,f,u) \;=\; \{\, z : u \to \bbr \;\mid\; \exists\, x \in X,\ \forall y \in u,\ f(x,y) < z_y \,\} \] of vectors that strictly dominate the payoff vector of some row on the sample $u$. This set is written $\texttt{OnlineLearning.finiteUpperImage}$ in Lean.
Statement
set_option relaxedAutoImplicit false in set_option autoImplicit false in open Real Finset BigOperators in def OnlineLearning.finiteUpperImage {Y : Set ℝ} (X : Set ℝ) (f : ℝ → ℝ → ℝ) (u : Finset Y) : Set (u → ℝ)
- Defined in
- TCSlib, `OnlineLearning.finiteUpperImage`
- 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.finiteUpperImage← OnlineLearning.finiteUpperImage (TCSlib/LearningTheory/Minimax/ConvexMinimaxSeparation.lean:65): verbatim
- Verified
- 07 Oct 2026
- Axioms
- none listed
- Used by 9
- OnlineLearning.finiteUpperImage_upperFinite upper image is upward closed. Let $X, Y \subseteq \bbr$, let $f : \bbr \to \bbr \to \bbr$ be a payoff, and let $u$ be a finite…
- OnlineLearning.finiteUpperImage_convexConvexity of the finite upper image. Let $X, Y \subseteq \bbr$, let $f : \bbr \to \bbr \to \bbr$ be a payoff, and let $u$ be a finite…
- 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 $u$…
- OnlineLearning.finiteUpperImage_isOpenThe finite upper image is open. Let $X, Y \subseteq \bbr$, let $f : \bbr \to \bbr \to \bbr$ be a payoff function, and let $u$ be a finite…
- OnlineLearning.separating_coordinate_nonposSeparating functional is coordinatewise nonpositive. Let $X, Y \subseteq \bbr$, let $f : \bbr \to \bbr \to \bbr$ be a payoff, let $u$ be a…
- 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…
- OnlineLearning.separating_functional_normalized_leNormalized separator bounds the constant by the average payoff. Let $X, Y \subseteq \bbr$, let $f : \bbr \to \bbr \to \bbr$ be a payoff,…
- OnlineLearning.separating_functional_ne_zeroA nonzero separating functional over the upper image. Let $X, Y \subseteq \bbr$, let $f : \bbr \to \bbr \to \bbr$ be a payoff, and let $u$…
- OnlineLearning.finite_sublevel_intersections_by_separationNonempty finite intersection of minimax sublevel sets. Let $X, Y \subseteq \bbr$ and $f : \bbr \times \bbr \to \bbr$ satisfy the…
Lean source view module on GitHub
set_option relaxedAutoImplicit false in set_option autoImplicit false in open Real Finset BigOperators in /-- The upper image of a finite column sample `u`: the set of vectors `z : u → ℝ` that lie strictly above the payoff vector `y ↦ f x y` of some row `x ∈ X` in every sampled coordinate. -/ def OnlineLearning.finiteUpperImage {Y : Set ℝ} (X : Set ℝ) (f : ℝ → ℝ → ℝ) (u : Finset Y) : Set (u → ℝ) := {z | ∃ x ∈ X, ∀ y : u, f x y < z y}