(28) — closed form of for the square loss and the squared cost (corrected at )
ProvedRWPI.SqrtLasso.eq_28distributionally-robust-optimizationlinear-regressionp2o-batch-pfp2bp2o-gran-per-chapterp2o-plan-paperp2o-v1
Fix and let satisfy . Let , , and let be a point. For the square loss and the cost , define . Then for every
This is the inner supremum of Proposition 1's dual in the setting of Proposition 2; with it the dual becomes a one-dimensional problem in .
Correction of the printed statement. The page gives for every . At the bracket is at most with , which is bounded (by ) when . The correction does not affect Proposition 2.
Formalization Note The point is a pair and is stack z; , are the norms of PiLp. The value is in ; is the mission's phi with the cost lqSqCost q.
Preamble
import Mathlib import Definitions.Def_RWPI_SqrtLasso_phi import Definitions.Def_RWPI_SqrtLasso_squareLoss import Definitions.Def_RWPI_SqrtLasso_lqSqCost
Formal statement
namespace RWPI.SqrtLasso
/-- Eq. (28) (App. A.1, proof of Proposition 2, p. 29), corrected at the boundary: the closed form
of `φ_γ` for the square loss and the squared `ℓ_q` cost on `ℝ^{d+1}`. With `x̄ = (x, y)`,
`β̄ = (−β, 1)` and `1/p + 1/q = 1`, for `γ ≥ 0`:
`φ_γ(x̄; β) = (β̄ᵀx̄)² γ / (γ − ‖β̄‖_p²)` if `γ > ‖β̄‖_p²`; `0` if `γ = ‖β̄‖_p²` and `β̄ᵀx̄ = 0`;
`+∞` otherwise. (The page prints `+∞` for all `γ ≤ ‖β̄‖_p²`, which is wrong at the single case
`γ = ‖β̄‖_p²`, `β̄ᵀx̄ = 0`.) -/
theorem eq_28 {d : ℕ} (q p : ENNReal) (hq : 1 < q) (hpq : p.HolderConjugate q)
(β : Fin d → ℝ) (z : (Fin d → ℝ) × ℝ) (γ : ℝ) (hγ : 0 ≤ γ) :
phi (lqSqCost q) (squareLoss β) γ z =
if ‖WithLp.toLp p (betaBar β)‖ ^ 2 < γ then
ENNReal.ofReal ((∑ j, betaBar β j * stack z j) ^ 2 * γ /
(γ - ‖WithLp.toLp p (betaBar β)‖ ^ 2))
else if γ = ‖WithLp.toLp p (betaBar β)‖ ^ 2 ∧ ∑ j, betaBar β j * stack z j = 0 then 0
else ⊤ := by sorry
end RWPI.SqrtLasso
Source
Blanchet, Kang & Murthy, Robust Wasserstein Profile Inference and Applications to Machine Learning, arXiv:1610.05627v4, p. 29, App. A.1, proof of Proposition 2, Eq. (28) (derivation from p. 28)
Human review
Confirmed by the mission captain (proposal self-audit).
Confirmed by the moderator at approval.