Fields- Workshop on Manifold and Graph-Based Learning

  1. Title:
    Stability and Generalization of Graph Neural Networks

    Speaker:

    Link:

  2. Title:
    Examples of Use of Multi-scale Techniques for Manifold Learning

    Speaker:

    Link:

  3. Title:
    Signal sampling by averages on Dirichlet spaces

    Speaker:

    Link:

  4. Title:
    Metric representations: Algorithms and Geometry

    Speaker:

    Link:

  5. Title:
    The Mathematics of Privacy and Synthetic Data

    Speaker:

    Link:

  6. Title:
    A tutorial on Manifold Learning for real data

    Speaker:

    Link:

  7. Title:
    Distributed algorithms for graph inverse filtering and wiener filtering

    Speaker:

    Link:

  8. Title:
    Learning graph signals and operators from sparse space-time samples

    Speaker:

    Link:

  9. Title:
    Statistical-to-Computational Gaps: The Low-Degree method and beyond

    Speaker:

    Link:

  10. Title:
    Geometry of Molecular Conformations in Cryo-EM

    Speaker:

    Link:

  11. Title:
    Sketch-and-solve approaches to k-means clustering by semidefinite programming

    Speaker:

    Link:

  12. Title:
    Multiscale Graph Basis Dictionaries

    Speaker:

    Link:

  13. Title:
    From Differentiable Reasoning to Self-supervised Embodied Active Learning

    Speaker:

    Link:

  14. Title:
    A Mini-Course On: Wasserstein Embeddings in Geometric Deep Learning (Part D)

    Speaker:

    Link:

  15. Title:
    A Mini-Course On: Wasserstein Embeddings in Geometric Deep Learning (Part C)

    Speaker:

    Link:

  16. Title:
    Self organizing mappings on the Grassmannian and Flag manifolds with applications to real world data

    Speaker:

    Link:

  17. Title:
    Measure Estimation in the Barycentric Coding Model: Geometry, Statistics, and Algorithms

    Speaker:

    Link:

  18. Title:
    Complex Structures on EEG data

    Speaker:

    Link:

  19. Title:
    Continuum Limits and Graph Cuts for Fermat Graph Laplacians

    Speaker:

    Link:

  20. Title:
    Statistical learning theory of deep neural networks for data on a low-dimensional manifold

    Speaker:

    Link: