hedgeWeight
defimported Lean
The unnormalized Hedge weight of expert $i$ at time $t$ with learning rate $\eta$ is \[ w_t(i) \;=\; \exp\!\bigl(-\eta \cdot L_t(i)\bigr). \] Experts with smaller cumulative loss receive larger weight.
Statement
set_option relaxedAutoImplicit false in set_option autoImplicit false in open Real Finset BigOperators in noncomputable def hedgeWeight {N T : ℕ} (η : ℝ) (ℓ : LossSeq N T) (t : ℕ) (i : Fin N) : ℝ
- Defined in
- TCSlib, `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.hedgeWeight← hedgeWeight (TCSlib/LearningTheory/Hedge/Basic.lean:95): verbatim
- Verified
- 07 Oct 2026
- Axioms
- none listed
- Built on 2
- Used by 6
- prefixHedgeWeight_eq_hedgeWeightPrefix Hedge weight agrees with the induced-loss Hedge weight. Let $G$ be a finite two-player zero-sum game with $M$ row actions and $N$…
- hedgeDistThe Hedge distribution at round $t$ is the normalization of the weight vector: \[ p_t(i) \;=\; \frac{w_t(i)}{W_t}. \]
- potential_ratio_lePotential ratio bound for Hedge. Fix $N \ge 1$ experts, a horizon of $T$ rounds, a learning rate $\eta > 0$, and a valid loss sequence…
- hedgeWeight_succRecursion for the Hedge weight. Fix a learning rate $\eta \in \bbr$ and a loss sequence $\ell$ for $N$ experts over $T$ rounds. For every…
- hedgeWeight_posPositivity of Hedge weights. Fix a learning rate $\eta \in \bbr$, a loss sequence $\ell$ for $N$ experts over $T$ rounds, a time $t$, and…
- potentialThe potential (sum of unnormalized weights) at time $t$ is \[ W_t \;=\; \sum_{i=1}^{N} w_t(i). \] The potential telescopes to…
Lean source view module on GitHub
set_option relaxedAutoImplicit false in set_option autoImplicit false in open Real Finset BigOperators in /-- The unnormalized Hedge weight `w_t(i) = exp(-η · L_t(i))` of expert `i` at round `t` [FS97, §2 (Hedge(β) with `β = e^{-η}`)]; [CBL06, §2.1]. Experts with smaller cumulative loss get larger exponential weight. -/ noncomputable def hedgeWeight {N T : ℕ} (η : ℝ) (ℓ : LossSeq N T) (t : ℕ) (i : Fin N) : ℝ := Real.exp (-η * cumLoss ℓ t i)