Budget Allocation for Unknown Value Functions in a Lipschitz Space

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Bateni, MohammadHossein, Esfandiari, Hossein, HosseinGhorban, Samira, Mirrokni, Alireza, Shahdaei, Radin
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914100388298752
author Bateni, MohammadHossein
Esfandiari, Hossein
HosseinGhorban, Samira
Mirrokni, Alireza
Shahdaei, Radin
author_facet Bateni, MohammadHossein
Esfandiari, Hossein
HosseinGhorban, Samira
Mirrokni, Alireza
Shahdaei, Radin
contents Building learning models frequently requires evaluating numerous intermediate models. Examples include models considered during feature selection, model structure search, and parameter tunings. The evaluation of an intermediate model influences subsequent model exploration decisions. Although prior knowledge can provide initial quality estimates, true performance is only revealed after evaluation. In this work, we address the challenge of optimally allocating a bounded budget to explore the space of intermediate models. We formalize this as a general budget allocation problem over unknown-value functions within a Lipschitz space.
format Preprint
id arxiv_https___arxiv_org_abs_2510_10605
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Budget Allocation for Unknown Value Functions in a Lipschitz Space
Bateni, MohammadHossein
Esfandiari, Hossein
HosseinGhorban, Samira
Mirrokni, Alireza
Shahdaei, Radin
Machine Learning
Building learning models frequently requires evaluating numerous intermediate models. Examples include models considered during feature selection, model structure search, and parameter tunings. The evaluation of an intermediate model influences subsequent model exploration decisions. Although prior knowledge can provide initial quality estimates, true performance is only revealed after evaluation. In this work, we address the challenge of optimally allocating a bounded budget to explore the space of intermediate models. We formalize this as a general budget allocation problem over unknown-value functions within a Lipschitz space.
title Budget Allocation for Unknown Value Functions in a Lipschitz Space
topic Machine Learning
url https://arxiv.org/abs/2510.10605