Generalization Below the Edge of Stability: The Role of Data Geometry
Fuente:
arXiv
Saved in:
| Main Authors: | Liang, Tongtong, Cloninger, Alexander, Parhi, Rahul, Wang, Yu-Xiang |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
Does Sparse Connectivity Improve Generalization? Convolutional Networks Below the Edge of Stability
by: Liang, Tongtong, et al.
Published: (2026)
by: Liang, Tongtong, et al.
Published: (2026)
Stable Minima of ReLU Neural Networks Suffer from the Curse of Dimensionality: The Neural Shattering Phenomenon
by: Liang, Tongtong, et al.
Published: (2025)
by: Liang, Tongtong, et al.
Published: (2025)
On the Loss Landscape Geometry of Regularized Deep Matrix Factorization: Uniqueness and Sharpness
by: Kamber, Anil, et al.
Published: (2026)
by: Kamber, Anil, et al.
Published: (2026)
Function-Space Optimality of Neural Architectures with Multivariate Nonlinearities
by: Parhi, Rahul, et al.
Published: (2023)
by: Parhi, Rahul, et al.
Published: (2023)
Sharpness of Minima in Deep Matrix Factorization
by: Kamber, Anil, et al.
Published: (2025)
by: Kamber, Anil, et al.
Published: (2025)
Finding Stable Subnetworks at Initialization with Dataset Distillation
by: McDermott, Luke, et al.
Published: (2025)
by: McDermott, Luke, et al.
Published: (2025)
Nonasymptotic Convergence Rates for Plug-and-Play Methods With MMSE Denoisers
by: Pritchard, Henry, et al.
Published: (2025)
by: Pritchard, Henry, et al.
Published: (2025)
A Gap Between the Gaussian RKHS and Neural Networks: An Infinite-Center Asymptotic Analysis
by: Kumar, Akash, et al.
Published: (2025)
by: Kumar, Akash, et al.
Published: (2025)
Point Cloud Classification via Deep Set Linearized Optimal Transport
by: Mahan, Scott, et al.
Published: (2024)
by: Mahan, Scott, et al.
Published: (2024)
Training Guarantees of Neural Network Classification Two-Sample Tests by Kernel Analysis
by: Khurana, Varun, et al.
Published: (2024)
by: Khurana, Varun, et al.
Published: (2024)
Towards Sharp Minimax Risk Bounds for Operator Learning
by: Adcock, Ben, et al.
Published: (2025)
by: Adcock, Ben, et al.
Published: (2025)
Variation Spaces for Multi-Output Neural Networks: Insights on Multi-Task Learning and Network Compression
by: Shenouda, Joseph, et al.
Published: (2023)
by: Shenouda, Joseph, et al.
Published: (2023)
Linearized Optimal Transport for Analysis of High-Dimensional Point-Cloud and Single-Cell Data
by: Wang, Tianxiang, et al.
Published: (2025)
by: Wang, Tianxiang, et al.
Published: (2025)
KAIROS: Scalable Model-Agnostic Data Valuation
by: Zhu, Jiongli, et al.
Published: (2025)
by: Zhu, Jiongli, et al.
Published: (2025)
LoLA: Low-Rank Linear Attention With Sparse Caching
by: McDermott, Luke, et al.
Published: (2025)
by: McDermott, Luke, et al.
Published: (2025)
OTClean: Data Cleaning for Conditional Independence Violations using Optimal Transport
by: Pirhadi, Alireza, et al.
Published: (2024)
by: Pirhadi, Alireza, et al.
Published: (2024)
When Data Falls Short: Grokking Below the Critical Threshold
by: Singh, Vaibhav, et al.
Published: (2025)
by: Singh, Vaibhav, et al.
Published: (2025)
Transformers for Learning on Noisy and Task-Level Manifolds: Approximation and Generalization Insights
by: Shen, Zhaiming, et al.
Published: (2025)
by: Shen, Zhaiming, et al.
Published: (2025)
Random ReLU Neural Networks as Non-Gaussian Processes
by: Parhi, Rahul, et al.
Published: (2024)
by: Parhi, Rahul, et al.
Published: (2024)
Linearized Optimal Transport pyLOT Library: A Toolkit for Machine Learning on Point Clouds
by: Linwu, Jun, et al.
Published: (2025)
by: Linwu, Jun, et al.
Published: (2025)
Robust Tangent Space Estimation via Laplacian Eigenvector Gradient Orthogonalization
by: Kohli, Dhruv, et al.
Published: (2025)
by: Kohli, Dhruv, et al.
Published: (2025)
Weighted variation spaces and approximation by shallow ReLU networks
by: DeVore, Ronald, et al.
Published: (2023)
by: DeVore, Ronald, et al.
Published: (2023)
Semi-Supervised Laplace Learning on Stiefel Manifolds
by: Holtz, Chester, et al.
Published: (2023)
by: Holtz, Chester, et al.
Published: (2023)
OT Score: An OT based Confidence Score for Prototype-Assisted Source Free Unsupervised Domain Adaptation
by: Zhang, Yiming, et al.
Published: (2025)
by: Zhang, Yiming, et al.
Published: (2025)
Isometric Immersion Learning with Riemannian Geometry
by: Chen, Zihao, et al.
Published: (2024)
by: Chen, Zihao, et al.
Published: (2024)
Spectral Concentration at the Edge of Stability: Information Geometry of Kernel Associative Memory
by: Tamamori, Akira
Published: (2025)
by: Tamamori, Akira
Published: (2025)
Robust Clustering using Hyperdimensional Computing
by: Ge, Lulu, et al.
Published: (2023)
by: Ge, Lulu, et al.
Published: (2023)
The Origin of Edge of Stability
by: Litman, Elon
Published: (2026)
by: Litman, Elon
Published: (2026)
Generalization at the Edge of Stability
by: Tuci, Mario, et al.
Published: (2026)
by: Tuci, Mario, et al.
Published: (2026)
Probe-Geometry Alignment: Erasing the Cross-Sequence Memorization Signature Below Chance
by: Rupa, Anamika Paul, et al.
Published: (2026)
by: Rupa, Anamika Paul, et al.
Published: (2026)
Semi-Supervised Manifold Learning with Complexity Decoupled Chart Autoencoders
by: Schonsheck, Stefan C., et al.
Published: (2022)
by: Schonsheck, Stefan C., et al.
Published: (2022)
LINSCAN -- A Linearity Based Clustering Algorithm
by: Dennehy, Andrew, et al.
Published: (2024)
by: Dennehy, Andrew, et al.
Published: (2024)
Edge of Stochastic Stability: Revisiting the Edge of Stability for SGD
by: Andreyev, Arseniy, et al.
Published: (2024)
by: Andreyev, Arseniy, et al.
Published: (2024)
Revisiting Meta-Learning with Noisy Labels: Reweighting Dynamics and Theoretical Guarantees
by: Zhang, Yiming, et al.
Published: (2025)
by: Zhang, Yiming, et al.
Published: (2025)
Geometry-Aware Edge Pooling for Graph Neural Networks
by: Limbeck, Katharina, et al.
Published: (2025)
by: Limbeck, Katharina, et al.
Published: (2025)
LayerPipe2: Multistage Pipelining and Weight Recompute via Improved Exponential Moving Average for Training Neural Networks
by: Unnikrishnan, Nanda K., et al.
Published: (2025)
by: Unnikrishnan, Nanda K., et al.
Published: (2025)
Optimal Recovery Meets Minimax Estimation
by: DeVore, Ronald, et al.
Published: (2025)
by: DeVore, Ronald, et al.
Published: (2025)
Product-Stability: Provable Convergence for Gradient Descent on the Edge of Stability
by: Gan, Eric
Published: (2026)
by: Gan, Eric
Published: (2026)
Adaptive Gradient Methods at the Edge of Stability
by: Cohen, Jeremy M., et al.
Published: (2022)
by: Cohen, Jeremy M., et al.
Published: (2022)
Zeroth-Order Optimization at the Edge of Stability
by: Song, Minhak, et al.
Published: (2026)
by: Song, Minhak, et al.
Published: (2026)
Similar Items
-
Does Sparse Connectivity Improve Generalization? Convolutional Networks Below the Edge of Stability
by: Liang, Tongtong, et al.
Published: (2026) -
Stable Minima of ReLU Neural Networks Suffer from the Curse of Dimensionality: The Neural Shattering Phenomenon
by: Liang, Tongtong, et al.
Published: (2025) -
On the Loss Landscape Geometry of Regularized Deep Matrix Factorization: Uniqueness and Sharpness
by: Kamber, Anil, et al.
Published: (2026) -
Function-Space Optimality of Neural Architectures with Multivariate Nonlinearities
by: Parhi, Rahul, et al.
Published: (2023) -
Sharpness of Minima in Deep Matrix Factorization
by: Kamber, Anil, et al.
Published: (2025)