Neural Feature Learning in Function Space

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Xu, Xiangxiang, Zheng, Lizhong
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929370509082624
author Xu, Xiangxiang
Zheng, Lizhong
author_facet Xu, Xiangxiang
Zheng, Lizhong
contents We present a novel framework for learning system design with neural feature extractors. First, we introduce the feature geometry, which unifies statistical dependence and feature representations in a function space equipped with inner products. This connection defines function-space concepts on statistical dependence, such as norms, orthogonal projection, and spectral decomposition, exhibiting clear operational meanings. In particular, we associate each learning setting with a dependence component and formulate learning tasks as finding corresponding feature approximations. We propose a nesting technique, which provides systematic algorithm designs for learning the optimal features from data samples with off-the-shelf network architectures and optimizers. We further demonstrate multivariate learning applications, including conditional inference and multimodal learning, where we present the optimal features and reveal their connections to classical approaches.
format Preprint
id arxiv_https___arxiv_org_abs_2309_10140
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Neural Feature Learning in Function Space
Xu, Xiangxiang
Zheng, Lizhong
Machine Learning
We present a novel framework for learning system design with neural feature extractors. First, we introduce the feature geometry, which unifies statistical dependence and feature representations in a function space equipped with inner products. This connection defines function-space concepts on statistical dependence, such as norms, orthogonal projection, and spectral decomposition, exhibiting clear operational meanings. In particular, we associate each learning setting with a dependence component and formulate learning tasks as finding corresponding feature approximations. We propose a nesting technique, which provides systematic algorithm designs for learning the optimal features from data samples with off-the-shelf network architectures and optimizers. We further demonstrate multivariate learning applications, including conditional inference and multimodal learning, where we present the optimal features and reveal their connections to classical approaches.
title Neural Feature Learning in Function Space
topic Machine Learning
url https://arxiv.org/abs/2309.10140