Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Explicit stochastic convex-bandit regret rate

Definition
LG2021_RegretRate

by sim2000dg · Nov 14, 2026 · Mathlib 0df444a (Lean v4.33.1)

convex-analysisonline-learningprobability

For dimension d≥1d\ge1d≥1, horizon n≥2n\ge2n≥2, and diameter D≥2D\ge2D≥2, define

R(d,D,n)=d9/2n [log⁡(nD)]3/2max⁡ ⁣{1,log⁡(nD)d}.R(d,D,n)=d^{9/2}\sqrt n\,[\log(nD)]^{3/2}\max\!\left\{1,\frac{\sqrt{\log(nD)}}{d}\right\}.R(d,D,n)=d9/2n​[log(nD)]3/2max{1,dlog(nD)​​}.

This is the explicit rate in Theorems 1 and 2 of Lattimore and György (COLT 2021). The Lean expression uses d4dd^4\sqrt dd4d​ and log⁡(nD)log⁡(nD)\log(nD)\sqrt{\log(nD)}log(nD)log(nD)​ for the fractional powers. This entry defines the rate; the regret guarantee is proved in the corresponding theorem entries.

Definition code
import Mathlib

noncomputable section

namespace LG2021

/-- The explicit dimension, horizon, and diameter dependence in the regret bound. -/
def sharpRate (d : ℕ) (D : ℝ) (n : ℕ) : ℝ :=
  (d : ℝ) ^ 4 * Real.sqrt d * Real.sqrt n *
    (Real.log ((n : ℝ) * D) * Real.sqrt (Real.log ((n : ℝ) * D))) *
      max 1 (Real.sqrt (Real.log ((n : ℝ) * D)) / (d : ℝ))

end LG2021
Source
Tor Lattimore and András György, Improved Regret for Zeroth-Order Stochastic Convex Bandits, Proceedings of the 34th Conference on Learning Theory (COLT 2021), Proceedings of Machine Learning Research 134:2938–2964, 2021, Theorems 1 and 2, printed p. 1.

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