pith. sign in

For the KBO regularization experiment, we useY=ω ⋆⊤ϕ(Z)+0.5η, which preservesEP [Y|X]and henceΨ ω(P), but introduces correlation between the outcome noise andZ

For the gradient estimation, inference experiments,Y=ω ⋆⊤ϕ(Z) +ε Y with εY ∼ N(0,0 · arXiv 7720.01680

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it
read on arXiv browse 1 citing papers

fields

stat.ML 1

years

2026 1

verdicts

UNVERDICTED 1

representative citing papers

Semiparametric Efficient Bilevel Gradient Estimation

stat.ML · 2026-05-20 · unverdicted · novelty 7.0

Introduces a cross-fitted orthogonal hypergradient estimator derived from the efficient influence function that achieves asymptotic normality and uniform control for bilevel gradient estimation under quadratic losses.

citing papers explorer

Showing 1 of 1 citing paper.

  • Semiparametric Efficient Bilevel Gradient Estimation stat.ML · 2026-05-20 · unverdicted · none · ref 64

    Introduces a cross-fitted orthogonal hypergradient estimator derived from the efficient influence function that achieves asymptotic normality and uniform control for bilevel gradient estimation under quadratic losses.