paper-with-me

Papers

Intrinsic Green's Learning: Supervised Learning on Manifolds via Inverse PDE

2026-07-08 · Alexandre Quemy arxiv

We introduce Intrinsic Green's Learning (IGL), a framework that models a target function on a manifold as the solution to a linear PDE whose source term is learned from data. Rather than approximating the target directly, IGL learns a source and integrates it against a Green's kernel. An encoder discovers a low-dimensional coordinate chart on the manifold where both the source and the kernel decompose as low-rank tensors, collapsing a high-dimensional integral into independent one-dimensional integrals with cost linear in the intrinsic dimension. A two-stage algorithm separates coordinate discovery from source fitting, a near-convex linear solve, preventing the dimensional collapse of joint training. Learnable gates on each coordinate automatically discover the intrinsic dimension of the manifold. We validate IGL on synthetic manifolds and on MNIST, where it simultaneously achieves near-optimal classification and automatic recovery of the intrinsic dimension.

📄 PDF Abstract BibTeX arXiv:2607.07034

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Exploring the Intrinsic Geometry of Diffusion Models with Constrained Inverse Kinematics

2026-06-24 · Miguel Angel Rogel Garcia, Phone Thiha Kyaw, Jonathan Kelly arxiv

Recent studies suggest that diffusion models can recover geometric structure in the data manifolds they are trained on, yet the supporting evidence has so far come mostly from natural-image data, where the underlying geo…

From the Greene--Wu Convolution to Gradient Estimation over Riemannian Manifolds

2021-08-17 · Tianyu Wang, Yifeng Huang, Didong Li

Over a complete Riemannian manifold of finite dimension, Greene and Wu introduced a convolution, known as Greene-Wu (GW) convolution. In this paper, we study properties of the GW convolution and apply it to non-Euclidean…

Verifying the Union of Manifolds Hypothesis for Image Data

2022-07-06 · Bradley C. A. Brown, Anthony L. Caterini, Brendan Leigh Ross, Jesse C. Cresswell 외

Deep learning has had tremendous success at learning low-dimensional representations of high-dimensional data. This success would be impossible if there was no hidden low-dimensional structure in data of interest; this e…

Inductive Bias

The Manifold Density Function: An Intrinsic Method for the Validation of Manifold Learning

2024-02-14 · Benjamin Holmgren, Eli Quist, Jordan Schupbach, Brittany Terese Fasy 외

We introduce the manifold density function, which is an intrinsic method to validate manifold learning techniques. Our approach adapts and extends Ripley's $K$-function, and categorizes in an unsupervised setting the ext…

Identification of release sources in advection-diffusion system by machine learning combined with Green function inverse method

2016-12-12 · Valentin G. Stanev, Filip L. Iliev, Scott Hansen, Velimir V. Vesselinov 외

The identification of sources of advection-diffusion transport is based usually on solving complex ill-posed inverse models against the available state- variable data records. However, if there are several sources with d…