prefixGameLoss
defimported Lean
Given a game $G$, a prefix of $t$ column actions, and a row $i$, the
prefix cumulative loss of row $i$ is
\[
L_t(i) \;=\; \sum_{s=0}^{t-1} \bigl(1 - A_{i, a_s}\bigr).
\]
This mirrors cumLoss from the abstract Hedge framework, expressed
directly in terms of game payoffs.
Statement
set_option relaxedAutoImplicit false in set_option autoImplicit false in open Real Finset BigOperators in noncomputable def prefixGameLoss {M N : ℕ} (G : ZeroSumGame M N) {t : ℕ} (actions : Fin t → Fin N) (i : Fin M) : ℝ
- Defined in
- TCSlib, `prefixGameLoss`
- 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.prefixGameLoss← prefixGameLoss (TCSlib/LearningTheory/Minimax/HedgeInteraction.lean:209): verbatim
- Verified
- 07 Oct 2026
- Axioms
- none listed
- Built on 1
- ZeroSumGameA finite two-player zero-sum game with $M$ row actions and $N$ column actions is a record consisting of a payoff matrix…
- Used by 2
- prefixHedgeWeightThe unnormalised Hedge weight of row $i$ after seeing a prefix of column actions at learning rate $\eta$ 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,…
Lean source view module on GitHub
set_option relaxedAutoImplicit false in set_option autoImplicit false in open Real Finset BigOperators in /-- The cumulative game loss `Σ_{s < t} (1 − A(i, j_s))` of row `i` along a finite prefix `j_0, …, j_{t−1}` of column actions. -/ noncomputable def prefixGameLoss {M N : ℕ} (G : ZeroSumGame M N) {t : ℕ} (actions : Fin t → Fin N) (i : Fin M) : ℝ := ∑ s : Fin t, (1 - G.payoff i (actions s))