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.
The sub-exponential tail bound gives, Pr 1 n n∑ 𝓁=j z2 j≥ x⋆Ωx⋆ +t ≤ exp [ −n/2 min((t/κ′ 1)2,t/κ′ 1) ] whereκ′ 1 = 8κ2/Cmin‖x⋆‖2
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.