A hierarchical Vovk-Azoury-Warmuth forecaster with discounting for online regression in RKHS

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autor principal: Rokhlin, Dmitry B.
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866908427046879232
author Rokhlin, Dmitry B.
author_facet Rokhlin, Dmitry B.
contents We study the problem of online regression with the unconstrained quadratic loss against a time-varying sequence of functions from a Reproducing Kernel Hilbert Space (RKHS). Recently, Jacobsen and Cutkosky (2024) introduced a discounted Vovk-Azoury-Warmuth (DVAW) forecaster that achieves optimal dynamic regret in the finite-dimensional case. In this work, we lift their approach to the non-parametric domain by synthesizing the DVAW framework with a random feature approximation. We propose a fully adaptive, hierarchical algorithm, which we call H-VAW-D (Hierarchical Vovk-Azoury-Warmuth with Discounting), that learns both the discount factor and the number of random features. We prove that this algorithm, which has a per-iteration computational complexity of $O(T\ln T)$, achieves an expected dynamic regret of $O(T^{2/3}P_T^{1/3} + \sqrt{T}\ln T)$, where $P_T$ is the functional path length of a comparator sequence.
format Preprint
id arxiv_https___arxiv_org_abs_2506_22631
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A hierarchical Vovk-Azoury-Warmuth forecaster with discounting for online regression in RKHS
Rokhlin, Dmitry B.
Machine Learning
68Q32, 68W27, 68W20
We study the problem of online regression with the unconstrained quadratic loss against a time-varying sequence of functions from a Reproducing Kernel Hilbert Space (RKHS). Recently, Jacobsen and Cutkosky (2024) introduced a discounted Vovk-Azoury-Warmuth (DVAW) forecaster that achieves optimal dynamic regret in the finite-dimensional case. In this work, we lift their approach to the non-parametric domain by synthesizing the DVAW framework with a random feature approximation. We propose a fully adaptive, hierarchical algorithm, which we call H-VAW-D (Hierarchical Vovk-Azoury-Warmuth with Discounting), that learns both the discount factor and the number of random features. We prove that this algorithm, which has a per-iteration computational complexity of $O(T\ln T)$, achieves an expected dynamic regret of $O(T^{2/3}P_T^{1/3} + \sqrt{T}\ln T)$, where $P_T$ is the functional path length of a comparator sequence.
title A hierarchical Vovk-Azoury-Warmuth forecaster with discounting for online regression in RKHS
topic Machine Learning
68Q32, 68W27, 68W20
url https://arxiv.org/abs/2506.22631