hedgeDist_nonneg
theoremverifiedimported Lean
Nonnegativity of the Hedge distribution. Fix $N \ge 1$ experts and $T$ rounds, a learning rate $\eta \in \bbr$, and a loss sequence $\ell$. For every time $t$ and every expert $i$, the Hedge distribution is nonnegative, that is, $p_t(i) \ge 0$.
Statement
set_option relaxedAutoImplicit false in set_option autoImplicit false in open Real Finset BigOperators in lemma hedgeDist_nonneg {N T : ℕ} [NeZero N] (η : ℝ) (ℓ : LossSeq N T) (t : ℕ) (i : Fin N) : 0 ≤ hedgeDist η ℓ t i
- Source
- TCSlib, `hedgeDist_nonneg`
- 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.hedgeDist_nonneg← hedgeDist_nonneg (TCSlib/LearningTheory/Hedge/Basic.lean:383): verbatim
- Verified
- 07 Oct 2026
- Axioms
Classical.choiceQuot.soundpropext- Built on 4
- hedgeDistThe Hedge distribution at round $t$ is the normalization of the weight vector: \[ p_t(i) \;=\; \frac{w_t(i)}{W_t}. \]
- potential_posPositivity of the Hedge potential. Fix a learning rate $\eta \in \bbr$, a loss sequence $\ell$ for $N \ge 1$ experts over $T$ rounds, and…
- hedgeWeight_posPositivity of Hedge weights. Fix a learning rate $\eta \in \bbr$, a loss sequence $\ell$ for $N$ experts over $T$ rounds, a time $t$, and…
- LossSeqA loss sequence $\ell$ for $N$ experts over $T$ rounds is a function $\ell : \mathrm{Fin}\,T \to \mathrm{Fin}\,N \to \mathbb{R}$,…
- Used by 3
- hedge_constructionHedge yields an approximate minimax pair. Let $G$ be a finite two-player zero-sum game with $M \ge 2$ row actions and $N \ge 1$ column…
- hedgeLoss_le_oneHedge's expected loss is at most one. Fix a learning rate $\eta \in \bbr$, and let $\ell$ be a valid loss sequence for $N \ge 1$ experts…
- hedgeLoss_nonnegNonnegativity of Hedge's expected loss. Let $\ell$ be a valid loss sequence for $N \ge 1$ experts over $T$ rounds, fix any learning rate…
Lean source view module on GitHub
set_option relaxedAutoImplicit false in set_option autoImplicit false in open Real Finset BigOperators in /-- Every coordinate of the Hedge distribution is nonnegative. -/ lemma hedgeDist_nonneg {N T : ℕ} [NeZero N] (η : ℝ) (ℓ : LossSeq N T) (t : ℕ) (i : Fin N) : 0 ≤ hedgeDist η ℓ t i := div_nonneg (hedgeWeight_pos η ℓ t i).le (potential_pos η ℓ t).le