paper-with-me

홈 › Papers

Local Hessian Spectral Filtering for Robust Intrinsic Dimension Estimation

2026-05-02 · Genki Osada arxiv

While diffusion models enable new approaches for estimating Local Intrinsic Dimension (LID), existing methods fail in high-dimensional spaces where noise from vast normal directions overwhelms the tangent signal. We propose Local Hessian Spectral Dimension (LHSD), which resolves this by applying spectral filtering to the log-density Hessian, explicitly cutting off large eigenvalues associated with normal directions to count zero-curvature tangent directions. Implemented using Stochastic Lanczos Quadrature (SLQ), LHSD avoids full Hessian construction, achieving linear scalability with dimension $D$. Experiments on synthetic and real data confirm LHSD's superior robustness and its utility in detecting memorization in large-scale diffusion models. The code is available at github.com/geosada/LHSD

📄 PDF Abstract BibTeX arXiv:2605.01221

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Finding Singular Features

2016-06-01 · Christopher Genovese, Marco Perone-Pacifico, Isabella Verdinelli, Larry Wasserman

We present a method for finding high density, low-dimensional structures in noisy point clouds. These structures are sets with zero Lebesgue measure with respect to the $D$-dimensional ambient space and belong to a $d<D$…

Clustering

From Zero to Hero: How local curvature at artless initial conditions leads away from bad minima

2024-03-04 · Tony Bonnaire, Giulio Biroli, Chiara Cammarota

We provide an analytical study of the evolution of the Hessian during gradient descent dynamics, and relate a transition in its spectral properties to the ability of finding good minima. We focus on the phase retrieval p…

Retrieval

DeStripe: A Self2Self Spatio-Spectral Graph Neural Network with Unfolded Hessian for Stripe Artifact Removal in Light-sheet Microscopy

2022-06-27 · Yu Liu, Kurt Weiss, Nassir Navab, Carsten Marr 외

Light-sheet fluorescence microscopy (LSFM) is a cutting-edge volumetric imaging technique that allows for three-dimensional imaging of mesoscopic samples with decoupled illumination and detection paths. Although the sele…

DenoisingGraph Neural Network

Rethinking Spectral Graph Neural Networks with Spatially Adaptive Filtering

2024-01-17 · Jingwei Guo, Kaizhu Huang, Xinping Yi, Zixian Su 외

Whilst spectral Graph Neural Networks (GNNs) are theoretically well-founded in the spectral domain, their practical reliance on polynomial approximation implies a profound linkage to the spatial domain. As previous studi…

Node Classification

Towards understanding the true loss surface of deep neural networks using random matrix theory and iterative spectral methods

2020-01-01 · ICLR 2020 1 · Diego Granziol, Timur Garipov, Dmitry Vetrov, Stefan Zohren 외

The geometric properties of loss surfaces, such as the local flatness of a solution, are associated with generalization in deep learning. The Hessian is often used to understand these geometric properties. We investigate…

GPU