Efficient Estimation of the Central Mean Subspace via Smoothed Gradient Outer Products

2023/12/24 by Gan Yuan, Yuan, Gan, Mingyue Xu +5 · 1 citation
Mathematics · #Statistical Methods and Inference #Statistical Methods and Bayesian Inference #Advanced Causal Inference Techniques

paper · pdf · doi:10.48550/arxiv.2312.15469

Abstract

We consider the problem of sufficient dimension reduction (SDR) for multi-index models. The estimators of the central mean subspace in prior works either have slow (non-parametric) convergence rates, or rely on stringent distributional conditions (e.g., the covariate distribution P_X being elliptical symmetric). In this paper, we show that a fast parametric convergence rate of form C_d ⋅ n^-1/2 is achievable via estimating the expected smoothed gradient outer product, for a general class of distribution P_X admitting Gaussian or heavier distributions. When the link function is a polynomial with a degree of at most r and P_X is the standard Gaussian, we show that the prefactor depends on the ambient dimension d as C_d ∝ d^r.

Cited by

• Local EGOP for Continuous Index Learning

Related

• Contraction rates and projection subspace estimation with Gaussian process priors in high dimension
• Smoothing the Landscape Boosts the Signal for SGD: Optimal Sample Complexity for Learning Single Index Models
• On the optimality of sliced inverse regression in high dimensions
• Convergence of Gaussian-smoothed optimal transport distance with sub-gamma distributions and dependent samples
• Nearest Neighbour Based Estimates of Gradients: Sharp Nonasymptotic Bounds and Applications