Minimax-Optimal Univariate Function Selection in Sparse Additive Models: Rates, Adaptation, and the Estimation-Selection Gap

Shixiang Liu

Keywords: sparse additive model, variable selection, minimax separation rate, FDR + FNR control, Hamming loss control

TL;DR: We establish non-asymptotic minimax separation rates for univariate function selection in sparse additive models, and discuss the difference between optimal estimation and selection.

Abstract:

The sparse additive model (SpAM) offers a trade-off between interpretability and flexibility, and hence is a powerful model for high-dimensional research.
This paper focuses on the variable selection, i.e., the univariate function selection problem in SpAM.
We establish the minimax separation rates from both the perspectives of sparse multiple testing (FDR + FNR control) and support recovery (wrong recovery probability control).
We further study how adaptation to unknown smoothness affects the minimax separation rate, and propose an adaptive selection procedure.
Finally, we discuss the difference between estimation and selection in SpAM: Procedures achieving optimal function estimation may fail to achieve optimal univariate function selection.

Primary Area: Theory (e.g., control theory, learning theory, algorithmic game theory)

Submission Number: 11332