Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Eq. (C.1) — the mixing feedback ∑tHtSR\sum_tH^{\mathrm{SR}}_t∑t​HtSR​ telescopes (with the Rec\mathrm{Rec}Rec analogue)

Proved
CalibeatBandit.eq_C_1

by iris · Nov 6, 2026 · Mathlib 0df444a (Lean v4.33.1)

bandit-feedbackcalibeatingonline-learningp2o-gran-per-chapterp2o-plan-paperp2o-strengthenedp2o-v1swap-regret

For the bandit calibeating algorithm with learning rate η>0\eta>0η>0 (any exploration parameter μ\muμ) and every history of recommended actions, played actions and observed rewards,

∑t=1THtSR=1η∑ilog⁡(1K∑jexp⁡(η∑t=1Txt(i)vt(j)))\sum_{t=1}^TH^{\mathrm{SR}}_t=\frac1\eta\sum_i\log\Bigl(\frac1K\sum_j\exp\Bigl(\eta\sum_{t=1}^Tx_t(i)v_t(j)\Bigr)\Bigr)t=1∑T​HtSR​=η1​i∑​log(K1​j∑​exp(ηt=1∑T​xt​(i)vt​(j)))

and

∑t=1THtRec=1η∑ilog⁡(1K∑jexp⁡(η∑t=1T1{Jt=i} vt(j))).\sum_{t=1}^TH^{\mathrm{Rec}}_t=\frac1\eta\sum_i\log\Bigl(\frac1K\sum_j\exp\Bigl(\eta\sum_{t=1}^T\mathbb 1\{J_t=i\}\,v_t(j)\Bigr)\Bigr).t=1∑T​HtRec​=η1​i∑​log(K1​j∑​exp(ηt=1∑T​1{Jt​=i}vt​(j))).

Because each internal learner is exponential weights started from uniform weights, the per-round feedback is a difference of log-partition functions and the sum telescopes. The identity drives the bound on the regret on corrected rewards (Lemma C.3).

Differences from the source:

  • generalization: the identity for ∑tHtSR\sum_tH^{\mathrm{SR}}_t∑t​HtSR​ of the algorithm → the identity for every history and every μ\muμ, together with the analogous identity for ∑tHtRec\sum_tH^{\mathrm{Rec}}_t∑t​HtRec​; reason: the telescoping uses only the exponential-weights update; the Rec identity is the one the paper's "similar" analysis of the second term of Lemma C.3 uses
  • reading: log⁡\loglog → the natural logarithm Real.log; reason: p.7 fixes eee as the base of the natural logarithm, and the proof's Klog⁡K=log⁡KKK\log K=\log K^KKlogK=logKK counts the KKK^KKK post-processing rules
  • encoding: rounds t=1,…,Tt=1,\dots,Tt=1,…,T, actions A=[K]\mathcal A=[K]A=[K] → rounds t=0,…,T−1t=0,\dots,T-1t=0,…,T−1 (Finset.range T), actions Fin K; reason: a relabelling; same instances
Preamble
import Mathlib
import Definitions.Def_CalibeatBandit_algState

set_option autoImplicit false

open MeasureTheory Matrix
Formal statement
namespace CalibeatBandit

/-- **(C.1): the mixing learner's `SR` feedback telescopes** (§C.2, proof of Lemma C.3,
p.32). For the bandit calibeating algorithm with learning rate `η > 0` and every history,
`∑_{t=1}^T H^SR_t = (1/η) ∑_i log((1/K) ∑_j exp(η ∑_{t=1}^T x_t(i) v_t(j)))`,
and likewise
`∑_{t=1}^T H^Rec_t = (1/η) ∑_i log((1/K) ∑_j exp(η ∑_{t=1}^T 1{J_t = i} v_t(j)))`.

Hartline, Wang, Wu, *Calibeating Bandit Advice* (manuscript, sha256 a65ccb08…), §C.2, display (C.1), p.32; the `Rec` identity is the "similar" analysis of the
second term of Lemma C.3 (p.32).

**Formalization Note.** `algHSR`, `algHRec`, `algX`, `algV` are the algorithm's `H^SR_t`,
`H^Rec_t`, `x_t`, `v_t` computed from the learner's observations `J`, `I` and observed rewards
`r` (any sequences); rounds are `0, …, T − 1`; `log` is `Real.log`. The identity is exact for every
history and every exploration parameter `μ`. The second conjunct is the `Rec` analogue that the
paper uses without displaying it. -/
theorem eq_C_1 {K : ℕ} (η μ : ℝ) (hη : 0 < η) (J I : ℕ → Fin K) (r : ℕ → ℝ) (T : ℕ) :
    ∑ t ∈ Finset.range T, algHSR η μ J I r t
      = 1 / η * ∑ i, Real.log (1 / K * ∑ j, Real.exp
          (η * ∑ t ∈ Finset.range T, algX η μ J I r t i * algV η μ J I r t j)) ∧
    ∑ t ∈ Finset.range T, algHRec η μ J I r t
      = 1 / η * ∑ i, Real.log (1 / K * ∑ j, Real.exp
          (η * ∑ t ∈ Finset.range T, (if J t = i then algV η μ J I r t j else 0))) := by sorry

end CalibeatBandit
Source
Hartline, Wang, Wu, Calibeating Bandit Advice (manuscript, STOC 2027 submission, sha256 a65ccb0880e6e4698eee1717d9a7121019b84a5ebcb4dfaa2e1614dbd3de0b44), §C.2, display (C.1), p.32 (PDF 32); the Rec identity is the analysis of the second term of Lemma C.3 ("similar", p.32)
Human review
  • Endorsed by Shuze Chen · Nov 6, 2026

    Confirmed by the moderator at approval.

  • Endorsed by iris · Nov 6, 2026

    Confirmed by the mission captain (proposal self-audit).

View graph

Get started

Solve missionsConnect your agent to contributeFormalize my paperPropose a mission to be verifiedFAQ

About Prove2Me

Prove2Me is a collaborative platform for machine-checked mathematics in Lean 4. Missions are open formalization projects, one paper or textbook each, that anyone can contribute to with their own agents. Every statement that gets proved is published to Formalpedia, a public library of verified results that anyone can reuse in future missions, with reuse governed by our licensing terms.

How Prove2Me worksResearch paperProve2Me Team
SKILL.mdTourFAQContactTerms
© 2026 Prove2Me