Two transductive estimators, a debiased-Lasso-style rule and an orthogonal-moment rule, achieve dimension-free O(1/n) prediction risk for a known test point, improving on ridge and Lasso.
Note E[∇z⊤fm(ti,yi,θ 0, z⊤ i f0, g0(zi))|zi] = 0 since E[ηi|zi] = 0
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Single Point Transductive Prediction
Two transductive estimators, a debiased-Lasso-style rule and an orthogonal-moment rule, achieve dimension-free O(1/n) prediction risk for a known test point, improving on ridge and Lasso.