No article text was recorded for this version.
progressive sharpening
Version 1 of 119 papers22 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Gradient Descent on Neural Networks Typically Occurs at the Edge of Stability
- Blog: Self-Stabilization: The Implicit Bias of Gradient Descent at the Edge of Stability
- Blog: Roughness Index for Loss Landscapes of Neural Network Models of Partial Differential Equations*
- Blog: Loss Spike in Training Neural Networks
- Blog: On the Relation Between the Sharpest Directions of DNN Loss and the SGD Step Length
- Blog: Universal Sharpness Dynamics in Neural Network Training: Fixed Point Analysis, Edge of Stability, and Route to Chaos
- Blog: Outliers with Opposing Signals Have an Outsized Effect on Neural Network Optimization
- Blog: A new characterization of the edge of stability based on a sharpness measure aware of batch gradient distribution
- Blog: Improving Generalization and Convergence by Enhancing Implicit Regularization
- Blog: A Minimalist Example of Edge-of-Stability and Progressive Sharpening
- Blog: Understanding the unstable convergence of gradient descent
- Blog: On progressive sharpening, flat minima and generalisation
- Blog: When and Why Momentum Accelerates SGD: An Empirical Study
- Blog: Second-order regression models exhibit progressive sharpening to the edge of stability
- Blog: Analyzing Sharpness along GD Trajectory: Progressive Sharpening and Edge of Stability
- Blog: Linear Mode Connectivity and the Lottery Ticket Hypothesis
- Blog: Understanding Sharpness Dynamics in NN Training with a Minimalist Example: The Effects of Dataset Difficulty, Depth, Stochasticity, and More
- Blog: On Gradient Descent Convergence beyond the Edge of Stability
- Blog: Large Catapults in Momentum Gradient Descent with Warmup: An Empirical Study
History & citation
Current · Permanent link
Cite this direction
Latest version (a living page):
@misc{lacuna_progressive_sharpening_687e57ff,
title = {progressive sharpening},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/progressive-sharpening/rdr_687e57ff653941169303ac0837d06687},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-20},
}This exact version (version 1, frozen text):
@misc{lacuna_progressive_sharpening_687e57ff_v1,
title = {progressive sharpening},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/progressive-sharpening/rdr_687e57ff653941169303ac0837d06687/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-20},
}