A Distributional View of High Dimensional Optimization

Fuente: arXiv
Saved in:
Bibliographic Details
Main Author: Benning, Felix
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915404307234816
author Benning, Felix
author_facet Benning, Felix
contents This PhD thesis presents a distributional view of optimization in place of a worst-case perspective. We motivate this view with an investigation of the failure point of classical optimization. Subsequently we consider the optimization of a randomly drawn objective function. This is the setting of Bayesian Optimization. After a review of Bayesian optimization we outline how such a distributional view may explain predictable progress of optimization in high dimension. It further turns out that this distributional view provides insights into optimal step size control of gradient descent. To enable these results, we develop mathematical tools to deal with random input to random functions and a characterization of non-stationary isotropic covariance kernels. Finally, we outline how assumptions about the data, specifically exchangability, can lead to random objective functions in machine learning and analyze their landscape.
format Preprint
id arxiv_https___arxiv_org_abs_2507_16315
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Distributional View of High Dimensional Optimization
Benning, Felix
Optimization and Control
Probability
Machine Learning
This PhD thesis presents a distributional view of optimization in place of a worst-case perspective. We motivate this view with an investigation of the failure point of classical optimization. Subsequently we consider the optimization of a randomly drawn objective function. This is the setting of Bayesian Optimization. After a review of Bayesian optimization we outline how such a distributional view may explain predictable progress of optimization in high dimension. It further turns out that this distributional view provides insights into optimal step size control of gradient descent. To enable these results, we develop mathematical tools to deal with random input to random functions and a characterization of non-stationary isotropic covariance kernels. Finally, we outline how assumptions about the data, specifically exchangability, can lead to random objective functions in machine learning and analyze their landscape.
title A Distributional View of High Dimensional Optimization
topic Optimization and Control
Probability
Machine Learning
url https://arxiv.org/abs/2507.16315