#spectral methods

try —

21 papers match

math.CO2026

ROSA: Metric Amplification on Noisy Graphs with Theoretical Guarantees for Amplified Spectral Distances

Ben Cardoen, Fabian Spill

The paper introduces ROSA, a robust order‑aware spectral amplification operator that strengthens graph distance metrics to more reliably detect weak, localized structural changes i…

#graph distances#spectral methods#noise robustness#metric amplification
gr-qc2026

Towards long and accurate numerical relativity waveforms of binary black holes beyond general relativity

Guillermo Lara, Harald P. Pfeiffer, Nils Deppe +9

The paper presents long, accurate numerical relativity simulations of equal‑mass, nonspinning binary black holes in shift‑symmetric scalar Gauss‑Bonnet gravity, generating waveform…

#numerical relativity#binary black holes#scalar gauss‑bonnet gravity#gravitational waveforms
math.NA2026

A Spectral-Domain Pseudo-Inverse Construction Method for Unitary Diagonalizable Linear Inverse Problems

Shengchang Chen

The paper proposes a spectral‑domain construction of a stable pseudo‑inverse for large linear inverse problems whose system matrix is unitary‑diagonalizable, using regularization f…

#inverse problems#spectral methods#pseudo-inverse#regularization
math.CO2026

A Spectral Proof of the Hypergraph Moore Bound

Alexander Schmidhuber, Matthew B. Hastings

The paper proves Feige's hypergraph Moore bound conjecture, showing that any sufficiently dense k‑uniform hypergraph contains a small even cover, using new spectral bounds for Kiku…

#hypergraph theory#even cover#Moore bound#spectral methods
cs.LG2026

SpectONet: A Physics-Guided Spectral Deep Operator Network for Euler-Bernoulli Beam Dynamics

Shivani Saini, Ramesh Kumar Vats, Arup Kumar Sahoo

The paper introduces SpectONet, a physics‑guided spectral deep operator network that combines DeepONet with physics‑informed constraints and nonuniform Chebyshev‑Gauss‑Lobatto sens…

#operator learning#physics-informed neural networks#spectral methods#structural dynamics
cs.LG2026

Flatness and Gradient Alignment Are Both Necessary: Spectral-Aware Gradient-Aligned Exploration for Multi-Distribution Learning

Aristotelis Ballas, Christos Diou

The paper shows that both loss‑landscape flatness and gradient alignment are essential for multi‑distribution learning and introduces SAGE, a method that jointly optimizes these pr…

#domain generalization#multi-task learning#sharpness-aware optimization#gradient alignment
cs.LG2026

Factorized Spectral Representations for Reinforcement Learning

Junyi Wu, Dan Li

The paper introduces FaStR, a method that factorizes the transition kernel of a reinforcement learning environment as a three-way tensor using CP decomposition, learning separate e…

#reinforcement learning#representation learning#spectral methods#tensor decomposition
math.NA2026

Spectral-Informed Neural Networks Outperform Spectral Methods in High-dimensional PDEs

Tianchi Yu, Ivan Oseledets

The paper introduces Modified Spectral-Informed Neural Networks (SINNs) that combine spectral methods with physics-informed neural networks, using coefficient decay scaling and bas…

#high-dimensional pdes#spectral methods#physics-informed neural networks#neural network approximation
math.CO2026

Spectral and Additive Combinatorial Methods for Cycles and Absorbing Sets in Lifted-Product Quantum LDPC Codes

Aida Abiad, Nichola Castriota

The paper develops spectral and additive combinatorial techniques to analyze short cycles and absorbing sets in lifted‑product quantum LDPC codes, providing closed‑form counts and…

#quantum ldpc codes#spectral methods#cycle counting#absorbing sets
physics.flu-dyn2026

Scale-conditioned structure-based closure for homogeneous turbulence: Ray-Column Interacting Particle Representation Model

Stavros C. Kassinos

The paper extends particle‑representation turbulence models by decomposing the spectral vector into orientation and radial wavenumber bands (the Ray‑Column approach) to retain scal…

#turbulence modeling#particle representation#spectral methods#closure models
gr-qc2026

Coupled by Design: Computing Kerr-Newman Quasinormal Modes with a Hybrid SpectralPINN Solver

Alexandre M. Pombo

The paper introduces a hybrid SpectralPINN solver for calculating quasinormal mode frequencies of charged Kerr‑Newman black holes by solving coupled gravitational and electromagnet…

#black hole quasinormal modes#kerr-newman spacetimes#physics-informed neural networks#spectral methods
cs.DC2026

DRIFT: Direct Reduced Fourier Transforms for Distributed Spectral Neural Operators

Sana Taghipour Anvari, David Kaeli

The paper introduces DRIFT, a GPU implementation that computes only the needed frequency modes for Fourier Neural Operators using a Distributed Truncated Spectral Transform, dramat…

#fourier neural operators#distributed training#gpu acceleration#spectral methods
quant-ph2026

An end-to-end quantum algorithm for weakly nonlinear plasma physics with superquadratic speedup

Bjorn K. Berntson, David Jennings, Matteo Lostaglio +1

The paper presents a complete quantum algorithm for simulating a weakly nonlinear kinetic plasma model, using Carleman linearization, hierarchical block encoding, and a specialized…

#quantum algorithms#plasma physics#nonlinear dynamics#carleman linearization
math.NA2026

An Adaptive Fourier Spectral Method for the Vlasov-Poisson system

Seung Yeon Cho, Giovanni Russo

The paper introduces an adaptive Fourier spectral method with high-order time splitting to dynamically expand the wavenumber domain and avoid artificial filtering when simulating t…

#vlasov-poisson#spectral methods#adaptive algorithms#phase-space filamentation
stat.ML2026

Spectral Diffusion Processes

Angus Phillips, Thomas Seror, Michael Hutchinson +3

The paper introduces diffusion models for stochastic processes by representing data in a spectral domain using kernels, truncating the spectral coefficients, and modeling them with…

#diffusion models#stochastic processes#spectral methods#conditional sampling
cs.RO2026

SPECTRA: Context-Conditioned Spectral Movement Primitives for Robot Skill Generalization

Boxuan Zhang, Sheng Liu, Chenlin Ming +1

The paper introduces Spectral Movement Primitives, a frequency‑domain approach that learns robot manipulation skills from demonstrations using low‑frequency Fourier coefficients an…

#imitation learning#movement primitives#spectral methods#robot manipulation
cs.CV2026

RealSkin: Spatio-Spectral Partial Neural Adjoint Maps for Image-to-3D Attribute Transfer

Jing Li, Yawei Luo, Xiangze Meng +3

RealSkin is a self‑supervised framework that transfers visual attributes from real photos onto synthetic 3D models by learning correspondences in a spectral domain and refining the…

#image-to-3d attribute transfer#partial correspondence#spectral methods#neural adjoint networks
math.NA2026

Explicit fractional Laplacians and Riesz potentials of classical functions

Timon S. Gutleb, Ioannis P. A. Papadopoulos

The paper derives explicit formulas for fractional Laplacians and their inverses (Riesz potentials) applied to classical orthogonal polynomials and Bessel functions, providing conc…

#fractional laplacian#riesz potential#orthogonal polynomials#spectral methods
math.AP2026

The CKN inequality for spinors: symmetry and symmetry breaking

Jean Dolbeault, Maria J. Esteban, Rupert L. Frank +1

The paper studies weighted Sobolev interpolation inequalities for spinor fields, examining when optimal spinors are symmetric and when symmetry breaks, using spectral analysis tech…

#spinors#caffarelli-kohn-nirenberg inequality#sobolev interpolation#symmetry breaking
cs.IR2026

From Embedding Geometry to Spectral Search: Energy Dispersion Networks For Vector Retrieval

Lorenzo Moriondo, Ilias Azizi

The paper proposes Graph Wiring, a framework that leverages spectral structure of embedding spaces for vector retrieval, and introduces Spectral Indexing, which combines geometric…

#vector search#spectral methods#embedding geometry#graph-based indexing
cs.LG2026

SPARC-Net: A Spectral, Causality-Aware, and Hard-Constrained Physics-Informed Architecture for Stiff and Shock-Dominated Partial Differential Equations

Divyavardhan Singh, Dimple Sonone, Hammad Mohammad +1

The paper introduces SPARC-Net, a physics-informed neural network architecture that combines spectral encoding, causality-aware training, and hard constraints to improve the soluti…

#physics-informed neural networks#partial differential equations#stiff problems#shock waves

One search, two signals: results blend meaning (embedding similarity, so papers that never use your words still surface) with keyword matches on titles, abstracts and summaries. Free, no sign-in needed.