Cover Image

Hardness of Learning Neural Networks under the Manifold Hypothesis

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Kiani, Bobak T., Wang, Jason, Weber, Melanie
Format:	Preprint
Published:	2024
Subjects:	Machine Learning Differential Geometry
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Learning Beyond Euclid: Curvature-Adaptive Generalization for Neural Networks on Manifolds
by: Sarkar, Krisanu
Published: (2025)

Neural Feature Geometry Evolves as Discrete Ricci Flow
by: Hehl, Moritz, et al.
Published: (2025)

Discretized Gradient Flow for Manifold Learning in the Space of Embeddings
by: Gold, Dara, et al.
Published: (2019)

Iso-Riemannian Optimization on Learned Data Manifolds
by: Diepeveen, Willem, et al.
Published: (2025)

Continuum Limits of Ollivier's Ricci Curvature on data clouds: pointwise consistency and global lower bounds
by: Trillos, Nicolas Garcia, et al.
Published: (2023)

Manifold Learning with Normalizing Flows: Towards Regularity, Expressivity and Iso-Riemannian Geometry
by: Diepeveen, Willem, et al.
Published: (2025)

Geometric and Spectral Alignment for Deep Neural Network I
by: Liu, Ziran, et al.
Published: (2026)

Geometric and Spectral Alignment for Deep Neural Network II
by: Liu, Ziran, et al.
Published: (2026)

Geometry-Aware Generative Autoencoders for Warped Riemannian Metric Learning and Generative Modeling on Data Manifolds
by: Sun, Xingzhi, et al.
Published: (2024)

Distance Measure Based on an Embedding of the Manifold of K-Component Gaussian Mixture Models into the Manifold of Symmetric Positive Definite Matrices
by: Vishwakarma, Amit, et al.
Published: (2025)

Staying on the Manifold: Geometry-Aware Noise Injection
by: Jacobsen, Albert Kjøller, et al.
Published: (2025)

Score-based Pullback Riemannian Geometry: Extracting the Data Manifold Geometry using Anisotropic Flows
by: Diepeveen, Willem, et al.
Published: (2024)

Manifold GCN: Diffusion-based Convolutional Neural Network for Manifold-valued Graphs
by: Hanik, Martin, et al.
Published: (2024)

Fiber Bundle Networks: A Geometric Machine Learning Paradigm
by: Liu, Dong
Published: (2025)

Chernoff Bounds for Tensor Expanders on Riemannian Manifolds Using Graph Laplacian Approximation
by: Chang, Shih-Yu
Published: (2024)

A singular Riemannian Geometry Approach to Deep Neural Networks III. Piecewise Differentiable Layers and Random Walks on $n$-dimensional Classes
by: Benfenati, Alessandro, et al.
Published: (2024)

GeoHNNs: Geometric Hamiltonian Neural Networks
by: Aboussalah, Amine Mohamed, et al.
Published: (2025)

Steerable Neural ODEs on Homogeneous Spaces
by: Andersdotter, Emma, et al.
Published: (2026)

Minimising Willmore Energy via Neural Flow
by: Hirst, Edward, et al.
Published: (2026)

Structured Regularization for Constrained Optimization on the SPD Manifold
by: Cheng, Andrew, et al.
Published: (2024)

The Geometric Wall: Manifold Structure Predicts Layerwise Sparse Autoencoder Scaling Laws
by: Zaher, Eslam, et al.
Published: (2026)

Pullback Flow Matching on Data Manifolds
by: de Kruiff, Friso, et al.
Published: (2024)

Deep Learning as Ricci Flow
by: Baptista, Anthony, et al.
Published: (2024)

Geometric Learning with Positively Decomposable Kernels
by: Da Costa, Nathael, et al.
Published: (2023)

Unitary convolutions for learning on graphs and groups
by: Kiani, Bobak T., et al.
Published: (2024)

Manifold Integrated Gradients: Riemannian Geometry for Feature Attribution
by: Zaher, Eslam, et al.
Published: (2024)

Sasaki Metric for Spline Models of Manifold-Valued Trajectories
by: Nava-Yazdani, Esfandiar, et al.
Published: (2023)

Logifold: A Geometrical Foundation of Ensemble Machine Learning
by: Jung, Inkee, et al.
Published: (2024)

Deep Generative Models: Complexity, Dimensionality, and Approximation
by: Wang, Kevin, et al.
Published: (2025)

Metric Flows with Neural Networks
by: Halverson, James, et al.
Published: (2023)

Approximate Ricci-flat Metrics for Calabi-Yau Manifolds
by: Lee, Seung-Joo, et al.
Published: (2025)

Cartan moving frames and the data manifolds
by: Tron, Eliot, et al.
Published: (2024)

Persistent de Rham-Hodge Laplacians in Eulerian representation for manifold topological learning
by: Su, Zhe, et al.
Published: (2024)

Revealing Decurve Flows for Generalized Graph Propagation
by: Lin, Chen, et al.
Published: (2024)

Thinner Latent Spaces: Detecting Dimension and Imposing Invariance with Conformal Autoencoders
by: Kevrekidis, George A., et al.
Published: (2024)

Jet Functors and Weil Algebras in Automatic Differentiation: A Geometric Analysis
by: Sangha, Amandip
Published: (2025)

Barycentric subspace analysis of network-valued data
by: Maignant, Elodie, et al.
Published: (2025)

Universal Collection of Euclidean Invariants between Pairs of Position-Orientations
by: Bellaard, Gijs, et al.
Published: (2025)

Roto-Translation Invariant Metrics on Position-Orientation Space
by: Bellaard, Gijs, et al.
Published: (2025)

Flow Matching on Lie Groups
by: Sherry, Finn M., et al.
Published: (2025)