AFTD Auto-Formalizing Theoretical Domains

hedgeDist_sum

theoremverifiedimported Lean

The Hedge distribution sums to one. Fix a number of experts $N \ge 1$, a horizon $T$, a learning rate $\eta \in \bbr$, a loss sequence $\ell$ for $N$ experts over $T$ rounds, and a round $t$. Then the Hedge distribution at round $t$ sums to one over all experts, \[ \sum_{i=1}^{N} p_t(i) = 1, \] so it is a probability distribution on the $N$ experts.

Statement

set_option relaxedAutoImplicit false in
set_option autoImplicit false in
open Real Finset BigOperators in
lemma hedgeDist_sum {N T : ℕ} [NeZero N] (η : ℝ) (ℓ : LossSeq N T) (t : ℕ) :
    ∑ i : Fin N, hedgeDist η ℓ t i = 1
Source
TCSlib, `hedgeDist_sum`
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.
Verified
07 Oct 2026
Axioms
Classical.choiceQuot.soundpropext
Built on 3
  • 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…
  • 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 2
  • 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…

Lean source view module on GitHub

set_option relaxedAutoImplicit false inset_option autoImplicit false inopen Real Finset BigOperators in/-- The Hedge distribution at any round is a probability vector: its coordinates sum to `1`. -/lemma hedgeDist_sum {N T : ℕ} [NeZero N] (η : ℝ) (ℓ : LossSeq N T) (t : ℕ) :    ∑ i : Fin N, hedgeDist η ℓ t i = 1 := by  -- Normalization by the positive potential turns weights into a probability  -- distribution.  simp only [hedgeDist]  rw [← Finset.sum_div]  exact div_self (ne_of_gt (potential_pos η ℓ t))
See it in the graphDiscuss this resultChallenge it