Guardado en:
Detalles Bibliográficos
Autores principales: Baby, Dheeraj, Tang, Yifei, Nguyen, Hieu Duy, Wang, Yu-Xiang, Pyati, Rohit
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:https://arxiv.org/abs/2505.15803
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866912386035744768
author Baby, Dheeraj
Tang, Yifei
Nguyen, Hieu Duy
Wang, Yu-Xiang
Pyati, Rohit
author_facet Baby, Dheeraj
Tang, Yifei
Nguyen, Hieu Duy
Wang, Yu-Xiang
Pyati, Rohit
contents In this paper, we study the problem of estimation and learning under temporal distribution shift. Consider an observation sequence of length $n$, which is a noisy realization of a time-varying groundtruth sequence. Our focus is to develop methods to estimate the groundtruth at the final time-step while providing sharp point-wise estimation error rates. We show that, without prior knowledge on the level of temporal shift, a wavelet soft-thresholding estimator provides an optimal estimation error bound for the groundtruth. Our proposed estimation method generalizes existing researches Mazzetto and Upfal (2023) by establishing a connection between the sequence's non-stationarity level and the sparsity in the wavelet-transformed domain. Our theoretical findings are validated by numerical experiments. Additionally, we applied the estimator to derive sparsity-aware excess risk bounds for binary classification under distribution shift and to develop computationally efficient training objectives. As a final contribution, we draw parallels between our results and the classical signal processing problem of total-variation denoising (Mammen and van de Geer,1997; Tibshirani, 2014), uncovering novel optimal algorithms for such task.
format Preprint
id arxiv_https___arxiv_org_abs_2505_15803
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Adaptive Estimation and Learning under Temporal Distribution Shift
Baby, Dheeraj
Tang, Yifei
Nguyen, Hieu Duy
Wang, Yu-Xiang
Pyati, Rohit
Machine Learning
In this paper, we study the problem of estimation and learning under temporal distribution shift. Consider an observation sequence of length $n$, which is a noisy realization of a time-varying groundtruth sequence. Our focus is to develop methods to estimate the groundtruth at the final time-step while providing sharp point-wise estimation error rates. We show that, without prior knowledge on the level of temporal shift, a wavelet soft-thresholding estimator provides an optimal estimation error bound for the groundtruth. Our proposed estimation method generalizes existing researches Mazzetto and Upfal (2023) by establishing a connection between the sequence's non-stationarity level and the sparsity in the wavelet-transformed domain. Our theoretical findings are validated by numerical experiments. Additionally, we applied the estimator to derive sparsity-aware excess risk bounds for binary classification under distribution shift and to develop computationally efficient training objectives. As a final contribution, we draw parallels between our results and the classical signal processing problem of total-variation denoising (Mammen and van de Geer,1997; Tibshirani, 2014), uncovering novel optimal algorithms for such task.
title Adaptive Estimation and Learning under Temporal Distribution Shift
topic Machine Learning
url https://arxiv.org/abs/2505.15803