Finite frozen doubled-amplitude training solution
ProvedQAlgorithms.Papers.Independent.Intakenext100.P88.amplitude_frozenUse the same ordered unitary circuit and normalized feature states, but output all complex amplitudes , . Duplicate each output as and . The worldsheet index therefore records whether an amplitude is conjugated. For real parameters, write .
Absorb the reference angles and rescale by . Let now be the doubled derivative with respect to at zero, and restrict to all doubled training coordinates . The initial residual is the first Taylor amplitude output at initial rescaled angles minus arbitrary complex training labels and their conjugates. For , the frozen recurrence has the solution
This finite solution preserves the real-loss normalization and requires no doubled-kernel inverse.
import Definitions.Def_QAlgorithms_Papers_Independent_Intakenext100_P88
noncomputable section
namespace QAlgorithms.Papers.Independent.Intakenext100.P88
open scoped BigOperators ComplexConjugate Topology NNReal ComplexOrder
open MeasureTheory ProbabilityTheory Filter
/-- PDF pp.30-31 Eqs.(152)-(154): finite frozen amplitude solution on doubled training
indices. The real gradient of half the complex squared loss produces eta/2.
No inverse or asymptotic interpolation claim is included. -/
theorem amplitude_frozen {D T : Type*} [Fintype T] [DecidableEq T] {h L : ℕ}
(M : AmplitudeModel D h L) (embed : T ↪ D)
(delta eta : ℝ) (hdelta : 0 < delta) (heta : 0 < eta)
(v : Fin L → ℝ) (y : T × Fin h → ℂ) (t : ℕ) :
let incl := fun a : T × Bool × Fin h => (embed a.1, a.2.1, a.2.2)
let K : Matrix (T × Bool × Fin h) (T × Bool × Fin h) ℂ := fun a b =>
frozenAmplitudeKernel M delta (incl a) (incl b)
let e : EuclideanSpace ℂ (T × Bool × Fin h) := WithLp.toLp 2 (fun a =>
doubledAmplitude M 0 (incl a) + (∑ l, amplitudeJet M delta (incl a) l * (v l : ℂ)) -
(if a.2.1 then star (y (a.1, a.2.2)) else y (a.1, a.2.2)))
frozenResidual K (eta / 2) e t = l2Action ((1 - (eta / 2) • K) ^ t) e := by sorry
end QAlgorithms.Papers.Independent.Intakenext100.P88
end
Read-back
What the Lean code literally says, in plain math · gpt-6.1-sol
Let be types with finite and with decidable equality, let be natural numbers, and let consist of , unitary matrices , Hermitian matrices , and unit vectors for . Define in increasing index order, and let and . Fix an injection , positive reals , , labels , and . Write , , , , and , . Define the complex Euclidean vector , and recursively define and . Then
This includes , allows , and allows to be empty; all derivatives are with respect to real coordinates, empty sums are zero, and the circuit’s empty product is the identity.
Confirmed by the mission captain (proposal self-audit).
Confirmed by the moderator at approval.