No article text was recorded for this version.
parameter blow-up
Version 1 of 114 papers20 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Blow up phenomena for gradient descent optimization methods in the training of artificial neural networks
- Blog: Logistic Regression, AdaBoost and Bregman Distances
- Blog: Does a sparse ReLU network training problem always admit an optimum ?
- Blog: The implicit bias of gradient descent on nonseparable data
- Blog: On Generalization of Decentralized Learning with Separable Data
- Blog: Gradient descent follows the regularization path for general losses
- Blog: Convex Risk Minimization and Conditional Probability Estimation
- Blog: On the existence of minimizers in shallow residual ReLU neural network optimization landscapes
- Blog: SAD Neural Networks: Divergent Gradient Flows and Asymptotic Optimality via o-minimal Structures
- Blog: Any-stepsize Gradient Descent for Separable Data under Fenchel–Young Losses
- Blog: The Fast Convergence of Boosting
- Blog: On skip connections and normalisation layers in deep optimisation
- Blog: Directional convergence and alignment in deep learning
- Blog: Implicit Bias of Mirror Flow on Separable Data
History & citation
Current · Permanent link
Cite this direction
Latest version (a living page):
@misc{lacuna_parameter_blow_up_69990fc1,
title = {parameter blow-up},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/parameter-blow-up/rdr_69990fc14ab247b6a7cd5e36c7c770d2},
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_parameter_blow_up_69990fc1_v1,
title = {parameter blow-up},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/parameter-blow-up/rdr_69990fc14ab247b6a7cd5e36c7c770d2/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-20},
}