The compensated per-action variable satisfies the scalar interface while the remaining-budget field has not crossed
ProvedG26G.Sharp.runF_SISetting. 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). The standing hypotheses Sharp hold: lies in the unit ball, , , is the unique minimizer of on , and the instance is sharp with modulus (H.sig): on . The corruption is bounded by : a.s. (IsCorruptedG). The projective body is and the cone body is ; , , and is the index of among the reference atoms (js).
Fix and a buffer sequence with , , an interval end , a start , and assume for . Consider the compensated variable
and the alive events (IW), where is the remaining-budget field of Lemma G.30. Then holds for with thresholds , budgets and .
On one has , because and the compensator differs from the shift by at most . The relative increment and conditional variance bounds come from Lemma G.10. These variables carry the far-reference estimate of Lemma G.29.
Formalization Note Rounds are 0-based.
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 G26G
open G26 G26R
variable {d : ℕ} {𝒜 ℬ : Set (Fin d → ℝ)} {e : ℕ → Fin d → ℚ} {θ astar : Fin d → ℝ}
variable {Ω : Type*} [mΩ : MeasurableSpace Ω] {P : Measure Ω} [IsProbabilityMeasure P]
{T : ℕ} {R : GRun d Ω}
open G26G.Sharp
variable (H : Sharp 𝒜 ℬ θ astar)
include Htheorem G26G.Sharp.runF_SI (hR : IsGIAFTRLRun P 𝒜 ℬ e T R) {C : ℝ} (hcor : IsCorruptedG P 𝒜 θ C T R)
{a : Fin d → ℝ} (ha : a ∈ Kset ℬ) {τ : ℕ → ℝ} (hτpos : ∀ n, 0 < τ n)
(hτmono : ∀ n, τ n ≤ τ (n + 1)) (hδ : ∀ n, τ (n + 1) - τ n ≤ 1) {m0 N : ℕ} (hN : N ≤ T)
(hτB : ∀ n, m0 ≤ n → gB d * (gbeta d (n + 1) + 3) ≤ τ n) :
SI P (Fx R T) (YF R θ astar C τ a) (IW 𝒜 ℬ R θ astar C τ m0) m0 N τ
(fun n => gbeta d (n + 1)) (gB d) := by sorry