cumLoss
defimported Lean
The cumulative loss of expert $i$ through the first $t$ rounds is \[ L_t(i) \;=\; \sum_{s < t} \ell_s(i), \] where the sum ranges over all rounds $s \in \mathrm{Fin}\,T$ with $s < t$.
Statement
set_option relaxedAutoImplicit false in set_option autoImplicit false in open Real Finset BigOperators in noncomputable def cumLoss {N T : ℕ} (ℓ : LossSeq N T) (t : ℕ) (i : Fin N) : ℝ
- Defined in
- TCSlib, `cumLoss`
- 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.cumLoss← cumLoss (TCSlib/LearningTheory/Hedge/Basic.lean:89): verbatim
- Verified
- 07 Oct 2026
- Axioms
- none listed
- Built on 1
- 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 7
- cumLoss_horizonCumulative loss at the horizon. Fix $N$ experts and a horizon $T$, and let $\ell$ be a loss sequence assigning to each round $t$ and…
- hedgeWeightThe unnormalized Hedge weight of expert $i$ at time $t$ with learning rate $\eta$ is…
- 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…
- 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,…
- bestExpertLossThe best expert loss in hindsight is the minimum cumulative loss achieved by any single expert:…
- cumLoss_succCumulative loss recurrence. Let $\ell$ be a loss sequence for $N$ experts over $T$ rounds, and write $L_t(i) = \sum_{s < t} \ell_s(i)$ for…
- potential_ge_best_expertPotential lower bound via the best expert. Fix $N \ge 1$ experts and $T$ rounds, a loss sequence $\ell$, and a learning rate $\eta > 0$.…
Lean source view module on GitHub
set_option relaxedAutoImplicit false in set_option autoImplicit false in open Real Finset BigOperators in /-- The cumulative loss `L_t(i) = ∑_{s < t} ℓ_s(i)` of expert `i` through the first `t` rounds [FS97, §2]; [CBL06, §2.1]. This sums exactly the rounds whose index is less than `t`. -/ noncomputable def cumLoss {N T : ℕ} (ℓ : LossSeq N T) (t : ℕ) (i : Fin N) : ℝ := ((Finset.univ (α := Fin T)).filter (fun s => s.val < t)).sum (fun s => ℓ s i)