No article text was recorded for this version.
lazy training regime (lazy training stability)
Version 1 of 138 papers49 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Gradient Descent Provably Optimizes Over-parameterized Neural Networks
- Blog: Width Independent Bounds for the Local Lipschitz Constant of Deep Neural Networks at Random Initialization and after Lazy Training
- Blog: Provable Accelerated Convergence of Nesterov's Momentum for Deep ReLU Neural Networks
- Blog: On the Diminishing Returns of Width for Continual Learning
- Blog: Widening the Network Mitigates the Impact of Data Heterogeneity on FedAvg
- Blog: Wide Neural Networks of Any Depth Evolve as Linear Models Under Gradient Descent
- Blog: One-pass Stochastic Gradient Descent in overparametrized two-layer neural networks
- Blog: SGD Learns the Conjugate Kernel Class of the Network
- Blog: Optimal Rates for Averaged Stochastic Gradient Descent under Neural Tangent Kernel Regime
- Blog: Gradient Descent Finds Global Minima of Deep Neural Networks
- Blog: Understanding the Dynamics of Gradient Flow in Overparameterized Linear models
- Blog: On the Convergence Analysis of Over-Parameterized Variational Autoencoders: A Neural Tangent Kernel Perspective
- Blog: On the Convergence of Shallow Neural Network Training with Randomly Masked Neurons
- Blog: Generalization Bounds of Stochastic Gradient Descent for Wide and Deep Neural Networks
- Blog: On the approximation of functions by tanh neural networks
- Blog: Understanding Over-parameterization in Generative Adversarial Networks
- Blog: On the Convergence Rate of Training Recurrent Neural Networks
- Blog: Random matrix analysis of deep neural network weight matrices
- Blog: Ridge Regression with Over-parametrized Two-Layer Networks Converge to Ridgelet Spectrum
- Blog: A Convergence Theory for Deep Learning via Over-Parameterization
- Blog: Unlocking the Potential of Federated Learning for Deeper Models
- Blog: The Dynamics of Gradient Descent for Overparametrized Neural Networks
- Blog: Neural tangent kernels, transportation mappings, and universal approximation
- Blog: Semi-flat minima and saddle points by embedding neural networks to overparameterization
- Blog: A global convergence theory for deep ReLU implicit networks via over-parameterization
- Blog: Neural Tangent Kernel: Convergence and Generalization in Neural Networks
- Blog: Spectral Signatures of Large Language Models
- Blog: Algorithm-Dependent Generalization Bounds for Overparameterized Deep Residual Networks
- Blog: Continual learning with the neural tangent ensemble
- Blog: On the Convergence of Two-Layer Kolmogorov-Arnold Networks with First-Layer Training
- Blog: The role of over-parametrization in generalization of neural networks
- Blog: Gradient descent GAN optimization is locally stable
- Blog: Polylogarithmic width suffices for gradient descent to achieve arbitrarily small test error with shallow ReLU networks
- Blog: Gradient descent optimizes over-parameterized deep ReLU networks
- Blog: A Generalized Neural Tangent Kernel Analysis for Two-layer Neural Networks
- Blog: Spectral Evolution and Invariance in Linear-width Neural Networks
- Blog: Generalization Error Bounds of Gradient Descent for Learning Over-Parameterized Deep ReLU Networks
- Blog: On the Convergence of Certified Robust Training with Interval Bound Propagation
History & citation
Current · Permanent link
- This direction split from Lazy Training Dynamics in Overparameterized Neural Networks (79% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_lazy_training_regime_lazy_training_stabi_cdbba317,
title = {lazy training regime (lazy training stability)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/lazy-training-regime-lazy-training-stability/rdr_cdbba317941e472bbb5242aa4a1076e7},
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_lazy_training_regime_lazy_training_stabi_cdbba317_v1,
title = {lazy training regime (lazy training stability)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/lazy-training-regime-lazy-training-stability/rdr_cdbba317941e472bbb5242aa4a1076e7/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-20},
}