paper-with-me

Papers

Spectral Diffusion Models on the Sphere

2026-01-28 · Francesco Mari, Pierpaolo Brutti, Claudio Durastanti arxiv

Diffusion models provide a principled framework for generative modeling via stochastic differential equations and time-reversed dynamics. However, extension of spectral diffusion approaches to spherical data raises nontrivial geometric and stochastic issues that are absent in the Euclidean setting. In this work, we develop a diffusion modeling framework defined directly on finite-dimensional spherical harmonic representations of real-valued functions on the sphere. We show that the spherical discrete Fourier transform maps spatial Brownian motion to a constrained Gaussian process in the frequency domain with deterministic, generally non-isotropic covariance. This induces modified forward- and reverse-time stochastic differential equations in the spectral domain. As a consequence, spatial and spectral score matching objectives are generally no longer equivalent, even in the band-limited setting. We establish a quantitative relationship between the two objectives, showing that the geometry-induced covariance of the spectral noise gives rise to a distinct, geometry-dependent inductive bias. We also derive the corresponding forward and reverse diffusion equations and characterize the induced noise covariance.

📄 PDF Abstract BibTeX arXiv:2601.20498

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

On a 'Two Truths' Phenomenon in Spectral Graph Clustering

2018-08-23 · Carey E. Priebe, Youngser Park, Joshua T. Vogelstein, John M. Conroy 외

Clustering is concerned with coherently grouping observations without any explicit concept of true groupings. Spectral graph clustering - clustering the vertices of a graph based on their spectral embedding - is commonly…

ClusteringDiffusion MRIGraph ClusteringSpectral Graph Clustering+1

SPHERE: Mitigating the Loss of Spectral Plasticity in Mixture-of-Experts for Deep Reinforcement Learning

2026-05-06 · Lirui Luo, Guoxi Zhang, Hongming Xu, Cong Fang 외 arxiv

In deep reinforcement learning (DRL), an agent is trained from a stream of experience. In a continual learning setting, such agents can suffer from plasticity loss: their ability to learn new skills from new experiences …

Reinforcement LearningContinual Learning

Controlled LLM Training on Spectral Sphere

2026-01-13 · Tian Xie, Haoming Luo, Haoyu Tang, Yiwen Hu 외 arxiv

Scaling large models requires optimization strategies that ensure rapid convergence grounded in stability. Maximal Update Parametrization ($\boldsymbolμ$P) provides a theoretical safeguard for width-invariant $Θ(1)$ acti…

Ill-posed Surface Emissivity Retrieval from Multi-Geometry Hyperspectral Images using a Hybrid Deep Neural Network

2021-07-09 · Fangcao Xu, Jian Sun, Guido Cervone, Mark Salvador

Atmospheric correction is a fundamental task in remote sensing because observations are taken either of the atmosphere or looking through the atmosphere. Atmospheric correction errors can significantly alter the spectral…

Retrieval

SpecSphere: Dual-Pass Spectral-Spatial Graph Neural Networks with Certified Robustness

2025-05-13 · Yoonhyuk Choi, Chong-Kwon Kim

We introduce SpecSphere, the first dual-pass spectral-spatial GNN that certifies every prediction against both $\ell\_{0}$ edge flips and $\ell\_{\infty}$ feature perturbations, adapts to the full homophily-heterophily s…

Node Classification