prefixHedgeWeight_eq_hedgeWeight
Prefix Hedge weight agrees with the induced-loss Hedge weight. Let $G$ be a finite two-player zero-sum game with $M$ row actions and $N$ column actions, with payoff matrix $A$, let $\eta \in \bbr$ be a learning rate, and let $a_0, \dots, a_{T-1}$ be a sequence of column actions, so that $a : \mathrm{Fin}\,T \to \mathrm{Fin}\,N$. Fix a round $t \in \mathrm{Fin}\,T$ and a row $i \in \mathrm{Fin}\,M$. Then the prefix Hedge weight of row $i$ at learning rate $\eta$, computed from the length-$t$ prefix $a_0, \dots, a_{t-1}$ of column actions, equals the Hedge weight of expert $i$ at time $t$ and learning rate $\eta$ for the loss sequence $\ell_s(j) = 1 - A_{j, a_s}$ induced by $G$ along $a$; that is, both equal \[ \exp\!\Bigl(-\eta \sum_{s < t} \bigl(1 - A_{i, a_s}\bigr)\Bigr). \]
Statement
set_option relaxedAutoImplicit false in set_option autoImplicit false in open Real Finset BigOperators in lemma prefixHedgeWeight_eq_hedgeWeight {M N T : ℕ} (G : ZeroSumGame M N) (η : ℝ) (actions : Fin T → Fin N) (t : Fin T) (i : Fin M) : prefixHedgeWeight G η (t := t.val) (fun s : Fin t.val => actions ⟨s.val, lt_trans s.isLt t.isLt⟩) i = hedgeWeight η (G.toLossSeq actions) t.val i
- Source
- TCSlib, `prefixHedgeWeight_eq_hedgeWeight`
- 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.prefixHedgeWeight_eq_hedgeWeight← prefixHedgeWeight_eq_hedgeWeight (TCSlib/LearningTheory/Minimax/HedgeInteraction.lean:302): verbatim
- Verified
- 07 Oct 2026
- Axioms
Classical.choiceQuot.soundpropext- Built on 5
- hedgeWeightThe unnormalized Hedge weight of expert $i$ at time $t$ with learning rate $\eta$ is…
- ZeroSumGameA finite two-player zero-sum game with $M$ row actions and $N$ column actions is a record consisting of a payoff matrix…
- prefixHedgeWeightThe unnormalised Hedge weight of row $i$ after seeing a prefix of column actions at learning rate $\eta$ is…
- ZeroSumGame.toLossSeqGiven a game $G$ and a sequence of column responses $j_0, \dots, j_{T-1}$, the induced loss sequence for the row player is…
- prefixGameLoss_eq_cumLossPrefix game loss equals induced cumulative loss. Let $G$ be a finite two-player zero-sum game with $M$ row actions and $N$ column actions,…
- Used by 2
- prefixHedgeMixedStrategy_weight_eq_hedgeDistPrefix Hedge strategy agrees with the abstract Hedge distribution. Let $G$ be a finite two-player zero-sum game with $M \ge 1$ row actions…
- prefixPotential_eq_potentialPrefix potential equals the induced Hedge potential. Let $G$ be a finite two-player zero-sum game with payoff matrix $A$ having $M$ rows…
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/-- The prefix Hedge weight of row `i` over the first `t` actions equals `hedgeWeight` at time `t` of the induced loss sequence. -/lemma prefixHedgeWeight_eq_hedgeWeight {M N T : ℕ} (G : ZeroSumGame M N) (η : ℝ) (actions : Fin T → Fin N) (t : Fin T) (i : Fin M) : prefixHedgeWeight G η (t := t.val) (fun s : Fin t.val => actions ⟨s.val, lt_trans s.isLt t.isLt⟩) i = hedgeWeight η (G.toLossSeq actions) t.val i := by simp only [prefixHedgeWeight, hedgeWeight] rw [prefixGameLoss_eq_cumLoss]