Saved in:
Bibliographic Details
Main Authors: Amin, Ahmad Ayaz, Kazi, Baha Uddin
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2509.25228
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914169709658112
author Amin, Ahmad Ayaz
Kazi, Baha Uddin
author_facet Amin, Ahmad Ayaz
Kazi, Baha Uddin
contents We introduce Random Projection Flows (RPFs), a principled framework for injective normalizing flows that leverages tools from random matrix theory and the geometry of random projections. RPFs employ random semi-orthogonal matrices, drawn from Haar-distributed orthogonal ensembles via QR decomposition of Gaussian matrices, to project data into lower-dimensional latent spaces for the base distribution. Unlike PCA-based flows or learned injective maps, RPFs are plug-and-play, efficient, and yield closed-form expressions for the Riemannian volume correction term. We demonstrate that RPFs are both theoretically grounded and practically effective, providing a strong baseline for generative modeling and a bridge between random projection theory and normalizing flows.
format Preprint
id arxiv_https___arxiv_org_abs_2509_25228
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Simple, Fast and Efficient Injective Manifold Density Estimation with Random Projections
Amin, Ahmad Ayaz
Kazi, Baha Uddin
Machine Learning
We introduce Random Projection Flows (RPFs), a principled framework for injective normalizing flows that leverages tools from random matrix theory and the geometry of random projections. RPFs employ random semi-orthogonal matrices, drawn from Haar-distributed orthogonal ensembles via QR decomposition of Gaussian matrices, to project data into lower-dimensional latent spaces for the base distribution. Unlike PCA-based flows or learned injective maps, RPFs are plug-and-play, efficient, and yield closed-form expressions for the Riemannian volume correction term. We demonstrate that RPFs are both theoretically grounded and practically effective, providing a strong baseline for generative modeling and a bridge between random projection theory and normalizing flows.
title Simple, Fast and Efficient Injective Manifold Density Estimation with Random Projections
topic Machine Learning
url https://arxiv.org/abs/2509.25228