High-dimensional Parameter Transfer With Fused-Regularizer

Дата публикации: 17-08-2026 20:26:00

Parameter transfer aims to improve parameter estimation accuracy by leveraging knowledge from related sources. This paper studies the parameter transfer problem from heterogeneous sources for high-dimensional M-estimators. Specifically, we propose a novel one-step estimator with a fused-regularizer and a target-data-oriented constraint, which can robustly capture parameter knowledge from source data in the presence of different types of data distribution shifts. Nonasymptotic bound is provided for the estimation error of target parameter, showing the proposed estimator could achieve effective parameter transfer under distribution shifts, and is guaranteed to perform no worse than any estimators learned only from the target data. We further show that the proposed estimator can achieve the minimax-optimal rate under much weaker conditions than existing methods. In addition, we extend the method to a distributed setting, requiring just one round of communication with source parameter estimators, while retaining the estimation accuracy of the centralized version. Extensive simulations and real data analysis further verify the effectiveness of the method.

Схожие новости

#	Наименование новости	Тональность	Информативность	Дата публикации
1	Communication-efficient Distributed Statistical Inference for Massive Data with Heterogeneous Auxiliary Information	0	7.7	17-08-2026
2	The Distribution of Ridgeless Least Squares Interpolators	0	5.78	17-08-2026
3	Near-optimal Delta-convex Estimation of Lipschitz Functions	0	9.71	17-08-2026
4	High-Dimensional Analysis of Gradient Flow for Extensive-Width Quadratic Neural Networks	0	8.7	17-08-2026
5	Transfer Conformal Predictive Inference for Regression	0	5.02	17-08-2026
6	Inference with non-differentiable surrogate loss in a general high-dimensional classification framework	0	8.38	17-08-2026
7	Extending Mean-Field Variational Inference via Entropic Regularization: Theory and Computation	0	8.7	17-08-2026
8	Knowledge Cascade: Reverse Knowledge Distillation on Nonparametric Multivariate Functional Estimation	0	5.75	17-08-2026
9	A causal fused lasso for interpretable heterogeneous treatment effects estimation	0	3.7	17-08-2026
10	Transfer Learning via Regularized Random-effects Linear Discriminant Analysis	0	5.98	17-08-2026

Классификация: Пресс-релизы. Схожих патентов: 0. Схожих новостей: 10. Тональность: 0. Информативность: 9.38. Источник: jmlr.org.