proofs
Provedalphabaguettebaguette-zcapstone

Baguette's actual moment banks satisfy m(t)² ≤ C²·v(t) at every step

For all g,m,v:N→R\htmlData{mx=3}{g, m, v : \htmlData{mx=0}{\mathbb{N}} \mathrel{\htmlData{mx=2}{\to}} \htmlData{mx=1}{\mathbb{R}}} and β1,β2∈R\htmlData{mx=1}{\beta_{1}, \beta_{2} \in \htmlData{mx=0}{\mathbb{R}}}, if 0<β20 \mathrel{\htmlData{mx=1}{<}} \htmlData{mx=0}{\beta_{2}}, β2<1\htmlData{mx=0}{\beta_{2}} \mathrel{\htmlData{mx=1}{<}} 1, β12<β2\htmlData{mx=1}{\htmlData{mx=0}{\beta_{1}}^{2}} \mathrel{\htmlData{mx=3}{<}} \htmlData{mx=2}{\beta_{2}}, m(0)=0\htmlData{mx=1}{\htmlData{mx=0}{m}(0)} \mathrel{\htmlData{mx=2}{=}} 0, v(0)=0\htmlData{mx=1}{\htmlData{mx=0}{v}(0)} \mathrel{\htmlData{mx=2}{=}} 0, ∀t, m(t+1)=β1⋅m(t)+(1−β1)⋅g(t)\htmlData{mx=17}{\forall t,\ \htmlData{mx=3}{\htmlData{mx=0}{m}(\htmlData{mx=2}{\htmlData{mx=1}{t} + 1})} \mathrel{\htmlData{mx=16}{=}} \htmlData{mx=15}{\htmlData{mx=8}{\htmlData{mx=4}{\beta_{1}} \cdot \htmlData{mx=7}{\htmlData{mx=5}{m}(\htmlData{mx=6}{t})}} + \htmlData{mx=14}{(\htmlData{mx=10}{1 - \htmlData{mx=9}{\beta_{1}}}) \cdot \htmlData{mx=13}{\htmlData{mx=11}{g}(\htmlData{mx=12}{t})}}}} and ∀t, v(t+1)=β2⋅v(t)+(1−β2)⋅g(t)2\htmlData{mx=18}{\forall t,\ \htmlData{mx=3}{\htmlData{mx=0}{v}(\htmlData{mx=2}{\htmlData{mx=1}{t} + 1})} \mathrel{\htmlData{mx=17}{=}} \htmlData{mx=16}{\htmlData{mx=8}{\htmlData{mx=4}{\beta_{2}} \cdot \htmlData{mx=7}{\htmlData{mx=5}{v}(\htmlData{mx=6}{t})}} + \htmlData{mx=15}{(\htmlData{mx=10}{1 - \htmlData{mx=9}{\beta_{2}}}) \cdot \htmlData{mx=14}{\htmlData{mx=13}{\htmlData{mx=11}{g}(\htmlData{mx=12}{t})}^{2}}}}}, then

∀t, m(t)2≤(1−β1)2(1−β2)⋅(1−β12β2)⋅v(t)\htmlData{mx=21}{\forall t,\ \htmlData{mx=3}{\htmlData{mx=2}{\htmlData{mx=0}{m}(\htmlData{mx=1}{t})}^{2}} \mathrel{\htmlData{mx=20}{\leq}} \htmlData{mx=19}{\htmlData{mx=15}{\frac{\htmlData{mx=6}{(\htmlData{mx=5}{1 - \htmlData{mx=4}{\beta_{1}}})^{2}}}{\htmlData{mx=14}{(\htmlData{mx=8}{1 - \htmlData{mx=7}{\beta_{2}}}) \cdot \left(\htmlData{mx=13}{1 - \htmlData{mx=12}{\frac{\htmlData{mx=10}{\htmlData{mx=9}{\beta_{1}}^{2}}}{\htmlData{mx=11}{\beta_{2}}}}}\right)}}} \cdot \htmlData{mx=18}{\htmlData{mx=16}{v}(\htmlData{mx=17}{t})}}}
What the notation means · or point at any symbol
NNatural numbers
The natural numbers 0, 1, 2, …. In Lean they start at 0. (ℕ)
⟹Implies
If ℕ, then ℝ. (Between types, A → B is the type of functions from A to B.) (ℕ → ℝ)
x : TVariables
g, m, v range over ℕ → ℝ: the statement must hold for every choice. ((g m v : ℕ → ℝ))
x ∈ TVariables
β₁, β₂ range over real numbers: the statement must hold for every choice. ((β₁ β₂ : ℝ))
<Less than
0 is strictly smaller than β₂. (0 < β₂)
aᵇPower
β₁ raised to the power 2. (β₁ ^ 2)
f(x)Function application
m applied to 0. Lean writes f x; papers write f(x). (m 0)
=Equality
m(0) and 0 are the same. (m 0 = 0)
∀For all
The statement after the comma holds for every t. (∀ t, m (t + 1) = β₁ * m t + (1 - β₁) * …)
RReal numbers
The real numbers: every point on the number line. (ℝ)
≤At most
m(t)^2 is less than or equal to (1 − β₁)^2/((1 − β₂) · (1 − β₁^2/β₂)) · v(t). (m t ^ 2 ≤ (1 - β₁) ^ 2 / ((1 - β₂) * (1…)
+Addition
t plus 1. (t + 1)
·Multiplication
β₁ times m(t). (β₁ * m t)
-Subtraction
1 minus β₁. On ℕ, Lean's subtraction stops at 0: 2 − 5 = 0. (1 - β₁)
a/bDivision
β₁^2 divided by β₂. In Lean, dividing by 0 gives 0. (β₁ ^ 2 / β₂)

Composes the closed forms of both moments (zero-initialized recurrences, as in Baguette's step-zero checkpoint) with the weighted Cauchy–Schwarz ratio: for every step t, m(t)² ≤ C²·v(t) with C² = (1−β₁)²/((1−β₂)(1−β₁²/β₂)). No assumption on gradient magnitude is needed. Part of the plan 'Baguette-Z: closed-loop certified integer-state training'.

How it was proved

Proved
3 October 2026
By
Ajax, with the agent “Baguette math & proofs (Claude Code, 2026-10-03)”
Checked by
Lean's kernel (Lean 4.33.1, with Mathlib); the proof is signed and replays offline
Axioms
Classical.choice, Quot.sound, propext
Proof
87 lines of Lean
Sign in to see the proofThe proof, its signed report and its history.

More proved statements