Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Proof of Theorem 2 — 1/β≤8(GD+1/α)1/\beta \le 8(GD + 1/\alpha)1/β≤8(GD+1/α)

Proved
LogRegretOCO.ONS.ons_beta_inv_bound

by mikedeng1 · Oct 30, 2026 · Mathlib 0df444a (Lean v4.33.1)

online-convex-optimizationonline-newton-step

Let G,D,α>0G, D, \alpha > 0G,D,α>0 and β=12min⁡{14GD,α}\beta = \tfrac12\min\{\tfrac{1}{4GD}, \alpha\}β=21​min{4GD1​,α}. Then

1β≤8(GD+1α).\frac{1}{\beta} \le 8\Bigl(GD + \frac{1}{\alpha}\Bigr).β1​≤8(GD+α1​).

This converts the regret bound n2βlog⁡T+12β\tfrac{n}{2\beta}\log T + \tfrac{1}{2\beta}2βn​logT+2β1​ into one in terms of the problem constants GGG, DDD and α\alphaα.

Differences from the source:

  • encoding: G, D positive implicitly (1/(4GD)); α > 0 standing (p. 173) → hypotheses 0 < G, 0 < D, 0 < α; reason: the conditions only exclude the cases in which β is undefined; α > 0 is the paper's own standing assumption
Preamble
import Mathlib
import Definitions.Def_LogRegretOCO_ONS_onsBeta
Formal statement
namespace LogRegretOCO.ONS

/-- **The constant `1/β ≤ 8(GD + 1/α)` (proof of Theorem 2).**
Hazan, Agarwal, Kale, *Logarithmic regret algorithms for online convex optimization*,
Machine Learning 69 (2007) 169–192, proof of Theorem 2, p. 179:
"Since β = 1/2 min{1/(4GD), α}, we have 1/β ≤ 8(GD + 1/α)."

**Formalization Note.** `G, D, α > 0` (the standing assumptions; `1/(4GD)` is otherwise
undefined). -/
theorem ons_beta_inv_bound {G D α : ℝ} (hG : 0 < G) (hD : 0 < D) (hα : 0 < α) :
    1 / onsBeta G D α ≤ 8 * (G * D + 1 / α) := by sorry

end LogRegretOCO.ONS
Source
Hazan, Agarwal, Kale, Logarithmic regret algorithms for online convex optimization, Machine Learning 69 (2007) 169–192, doi:10.1007/s10994-007-5016-8, proof of Theorem 2, last paragraph, p. 179 (PDF p. 11)

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