Asymptotic Distribution of Low-Dimensional Patterns Induced by Non-Differentiable Regularizers under General Loss Functions

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Hejný, Ivan, Wallin, Jonas, Bogdan, Małgorzata
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911269352636416
author Hejný, Ivan
Wallin, Jonas
Bogdan, Małgorzata
author_facet Hejný, Ivan
Wallin, Jonas
Bogdan, Małgorzata
contents This article investigates the asymptotic distribution of penalized estimators with non-differentiable penalties designed to recover low-dimensional pattern structures. Patterns play a central role in estimation, as they reveal the underlying structure of the parameter -- which coefficients are zero, which are equal, and how they are clustered. The main technical challenge stems from the discontinuous nature of these patterns (such as the sign function in the case of the Lasso penalty), a difficulty not previously addressed in the literature and only recently analyzed for the standard linear model. To overcome this, we extend classical results from empirical process theory for M-estimation by incorporating the distributional behavior of model patterns. We introduce a new mathematical framework for studying pattern convergence of regularized M-estimators. While classical approaches to distributional convergence rely on uniform conditions, our analysis employs a new local condition, stochastic Lipschitz differentiability (SLD), which controls fluctuations of the Taylor remainder. We demonstrate how this framework applies to a broad class of loss functions, covering generalized linear models (e.g., logistic and Poisson regression) and robust regression settings with non-smooth losses such as the Huber and quantile loss.
format Preprint
id arxiv_https___arxiv_org_abs_2506_12621
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Asymptotic Distribution of Low-Dimensional Patterns Induced by Non-Differentiable Regularizers under General Loss Functions
Hejný, Ivan
Wallin, Jonas
Bogdan, Małgorzata
Statistics Theory
62J07 (Primary), 62F35, 62J12 (Secondary)
This article investigates the asymptotic distribution of penalized estimators with non-differentiable penalties designed to recover low-dimensional pattern structures. Patterns play a central role in estimation, as they reveal the underlying structure of the parameter -- which coefficients are zero, which are equal, and how they are clustered. The main technical challenge stems from the discontinuous nature of these patterns (such as the sign function in the case of the Lasso penalty), a difficulty not previously addressed in the literature and only recently analyzed for the standard linear model. To overcome this, we extend classical results from empirical process theory for M-estimation by incorporating the distributional behavior of model patterns. We introduce a new mathematical framework for studying pattern convergence of regularized M-estimators. While classical approaches to distributional convergence rely on uniform conditions, our analysis employs a new local condition, stochastic Lipschitz differentiability (SLD), which controls fluctuations of the Taylor remainder. We demonstrate how this framework applies to a broad class of loss functions, covering generalized linear models (e.g., logistic and Poisson regression) and robust regression settings with non-smooth losses such as the Huber and quantile loss.
title Asymptotic Distribution of Low-Dimensional Patterns Induced by Non-Differentiable Regularizers under General Loss Functions
topic Statistics Theory
62J07 (Primary), 62F35, 62J12 (Secondary)
url https://arxiv.org/abs/2506.12621