Overview

Spectral methods study problems by expressing data or operators in terms of eigenvalues, eigenvectors, or frequency modes. Classical approaches include Fourier and graph-Laplacian transforms, PCA and low-rank approximation, kernel methods, and polynomial filters; they are used for tasks such as clustering networks, estimating dimensions, and solving or learning partial differential equations. Newer work also uses spectral structure to design neural operators and optimizers, diagnose model behavior, and speed up large matrix computations. A central challenge is balancing efficient, robust approximations with the assumptions and information lost when choosing a fixed basis, truncating modes, or relying on noisy spectra.

Latest papers

CardsList

247 papers11 papers in the last four weeks, down 56% on the four weeks before. 0.1% of all new papers.

  1. Physics-Informed Support Vector Kernels via Green-Function Analogies and Jackson-Chebyshev Spectral Design

    Feb 16, 2025Nan-Hong Kuo, Renata WongSupport Vector MachinesKernel Methods

  2. Fixed-Gaussian Spectral Algorithms: Minimax Optimal Rates for Misspecified Learning and Transfer

    Jan 18, 2025Haotian Lin, Matthew ReimherrSpectral RegularizationConcept Drift

  3. Adversarial dynamical systems characterize when data-driven learning succeeds or fails

    Jul 8, 2024Matthew J. Colbrook, Igor Mezić, Alexei StepanenkoKoopman Operator LearningSpectral Methods

  4. Hearing the shape of an arena with spectral swarm robotics

    Mar 25, 2024Leo Cazenille, Nicolas Lobato-Dauzier, Alessia Loi +7Swarm RoboticsSpectral Methods

  5. FC-PINO: High Precision Physics-Informed Neural Operators via Fourier Continuation

    Nov 29, 2022Adarsh Ganeshram, Valentin Duruisseaux, Haydn Maust +6Physics-Informed Neural OperatorsPDE Solving

  6. Robust Streaming PCA

    Feb 8, 2019Daniel Bienstock, Minchan Jeong, Apurv Shukla +1Principal Component AnalysisStreaming Algorithms