AFTD Auto-Formalizing Theoretical Domains

prefixPotential_pos

theoremverifiedimported Lean

Positivity of the prefix potential. Let $G$ be a finite two-player zero-sum game with at least one row action, fix a learning rate $\eta \in \bbr$, and let $a_0, \dots, a_{t-1}$ be any prefix of column actions. Then the prefix potential is strictly positive, \[ \Phi_t \;=\; \sum_{i} \exp\!\bigl(-\eta\, L_t(i)\bigr) \;>\; 0, \] where $L_t(i)$ is the prefix cumulative loss of row $i$.

Statement

set_option relaxedAutoImplicit false in
set_option autoImplicit false in
open Real Finset BigOperators in
lemma prefixPotential_pos {M N : ℕ} [NeZero M] (G : ZeroSumGame M N)
    (η : ℝ) {t : ℕ} (actions : Fin t → Fin N) :
    0 < prefixPotential G η actions
Source
TCSlib, `prefixPotential_pos`
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 4
  • prefixPotentialThe prefix potential is the sum of prefix Hedge weights over all rows: \[ \Phi_t \;=\; \sum_{i \in \mathrm{Fin}\,M} w_t(i). \]
  • ZeroSumGameA finite two-player zero-sum game with $M$ row actions and $N$ column actions is a record consisting of a payoff matrix…
  • prefixHedgeWeight_posPositivity of the prefix Hedge weight. Let $G$ be a finite two-player zero-sum game with $M$ row actions and $N$ column actions, let…
  • prefixHedgeWeightThe unnormalised Hedge weight of row $i$ after seeing a prefix of column actions at learning rate $\eta$ is…
Used by 1
  • prefixHedgeMixedStrategyThe normalised Hedge distribution after a prefix of $t$ column actions is the mixed row strategy with weights…

Lean source view module on GitHub

set_option relaxedAutoImplicit false inset_option autoImplicit false inopen Real Finset BigOperators in/-- The prefix potential is strictly positive when there is at least one row, being a nonempty sum of positive weights. -/lemma prefixPotential_pos {M N : ℕ} [NeZero M] (G : ZeroSumGame M N)    (η : ℝ) {t : ℕ} (actions : Fin t → Fin N) :    0 < prefixPotential G η actions := by  apply Finset.sum_pos  · intro i _    exact prefixHedgeWeight_pos G η actions i  · exact Finset.univ_nonempty
See it in the graphDiscuss this resultChallenge it