The loss-difference field of a GIA-FTRL run on K satisfies the field interface
ProvedG26R.runK_FISetting. is a compact action set spanning , is a compact generator (), is the direction enumeration, and is a GIA-FTRL run of rounds (IsGIAFTRLRun) with cumulative loss estimate , run filtration , learning rate (gbeta) and magnitude constant (gB). The filtration used below is for and (Fx).
Assume , compact, a generator of , , and let . Consider the affine field on
Then satisfies the field interface on with alive events , budgets and , drift range , and start :
The conditional mean of an increment is (unbiased estimates, actions and losses in the unit ball), and the magnitude and second-moment budgets are the universal bounds (G.153)–(G.154) of Lemma G.10. This yields the absolute envelopes of Lemma G.15.
Formalization Note Rounds are 0-based: sums the estimates of run rounds .
import Mathlib
import Definitions.Def_IAFTRL_LinEnv
import Definitions.Def_IAFTRL_GIAFTRL
import Definitions.Def_IAFTRL_G26_body
import Definitions.Def_IAFTRL_G26_run
import Definitions.Def_IAFTRL_G26_window
open MeasureTheory ProbabilityTheory Set IAFTRL Matrix
open G26R
open G26
variable {d : ℕ} {𝒜 ℬ : Set (Fin d → ℝ)} {e : ℕ → Fin d → ℚ}
variable {Ω : Type*} [mΩ : MeasurableSpace Ω] {P : Measure Ω} [IsProbabilityMeasure P]
{T : ℕ} {R : GRun d Ω}theorem G26R.runK_FI (hd : 1 ≤ d) (h𝒜 : IsCompact 𝒜) (hℬ : IsCompact ℬ) (hgen : IsGenerator 𝒜 ℬ)
(hspan : Submodule.span ℝ 𝒜 = ⊤) (hR : IsGIAFTRLRun P 𝒜 ℬ e T R) {astar : Fin d → ℝ}
(haK : astar ∈ Kset ℬ) :
FI (Kset ℬ) P (Fx R T) T R.cumEst (fun n ω => -(astar ⬝ᵥ R.cumEst n ω)) (fun _ => univ)
(fun n => gbeta d (n + 1)) (gB d) (-2) 2 0 := by sorry