Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Theorem 8.1 — with η anomalies, opt(F, η) ≥ opt(F, 0) + 2η for every class with |F| > 1

Proved
WeightedMajority.Anomalies.theorem_8_1

by mikedeng1 · Oct 6, 2026 · Mathlib 0df444a (Lean v4.33.1)

anomalieslower-boundmistake-boundonline-learningp2o-batch-pfp2bp2o-gran-per-chapterp2o-plan-paperp2o-v1weighted-majority

Let XXX be an arbitrary domain and FFF a class of {0,1}\{0,1\}{0,1}-valued functions on XXX, possibly infinite, with at least two members. For η∈{0,1,2,… }\eta \in \{0,1,2,\dots\}η∈{0,1,2,…} let opt(F,η)\mathrm{opt}(F,\eta)opt(F,η) be the minimum, over all deterministic on-line prediction algorithms AAA, of the maximum number of mistakes AAA makes on a finite sequence of trials having at most η\etaη anomalies with respect to FFF (some f∈Ff \in Ff∈F disagrees with at most η\etaη of its labels). Then

opt(F,η) ≥ opt(F,0)+2η.\mathrm{opt}(F,\eta) \ \ge\ \mathrm{opt}(F,0) + 2\eta .opt(F,η) ≥ opt(F,0)+2η.

Each anomaly the adversary is allowed therefore costs every deterministic learner at least two additional mistakes beyond the optimal noise-free bound. The theorem shows that the deterministic Weighted Majority algorithm, whose mistake bound grows at a rate that can be made arbitrarily close to 222 per anomaly by the choice of β\betaβ, has an essentially optimal rate of growth in the number of anomalies.

Formalization Note Values are in N∪{∞}\mathbb N \cup \{\infty\}N∪{∞} (ℕ∞); when opt(F,0)=∞\mathrm{opt}(F,0) = \inftyopt(F,0)=∞ the statement says opt(F,η)=∞\mathrm{opt}(F,\eta) = \inftyopt(F,η)=∞. The hypothesis ∣F∣>1|F| > 1∣F∣>1 is F.Nontrivial (two distinct members), which also covers infinite classes.

Preamble
import Mathlib
import Definitions.Def_UnderstandingML_Online
import Definitions.Def_WeightedMajority_Anomalies_Opt
Formal statement
namespace WeightedMajority.Anomalies

/-- Littlestone and Warmuth's Theorem 8.1 (p. 250): for every class `F` of `{0,1}`-valued
functions with `|F| > 1` and every `η ≥ 0`, `opt(F, η) ≥ opt(F, 0) + 2η`. -/
theorem theorem_8_1 {X : Type*} (F : Set (X → Bool)) (hF : F.Nontrivial) (η : ℕ) :
    opt F 0 + 2 * (η : ℕ∞) ≤ opt F η := by sorry

end WeightedMajority.Anomalies
Source
Littlestone, Warmuth, The Weighted Majority Algorithm, Inform. and Comput. 108 (1994), p. 250, Theorem 8.1
Human review
  • Endorsed by Shuze Chen · Oct 6, 2026

    Confirmed by the moderator at approval.

  • Endorsed by mikedeng1 · Oct 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