No article text was recorded for this version.
over-parameterized global convergence
Version 1 of 134 papers37 conceptsfrozen 2026-10-04
Papers in this version
- Blog: On the Convergence Rate of Training Recurrent Neural Networks
- Blog: On the Proof of Global Convergence of Gradient Descent for Deep ReLU Networks with Linear Widths
- Blog: Theoretical insights into the optimization landscape of over-parameterized shallow neural networks
- Blog: Provable Accelerated Convergence of Nesterov's Momentum for Deep ReLU Neural Networks
- Blog: Global optimality of Elman-type RNNs in the mean-field regime
- Blog: Convergence beyond the over-parameterized regime using Rayleigh quotients
- Blog: Provably Efficient Neural Estimation of Structural Equation Models: An Adversarial Approach
- Blog: Global Convergence of MAML and Theory-Inspired Neural Architecture Search for Few-Shot Learning
- Blog: Gradient Descent Provably Optimizes Over-parameterized Neural Networks
- Blog: Global Optimality in Neural Network Training
- Blog: On the Power of Over-parametrization in Neural Networks with Quadratic Activation
- Blog: The Loss Surface of Deep and Wide Neural Networks
- Blog: Convergence Rates of Non-Convex Stochastic Gradient Descent Under a Generic Lojasiewicz Condition and Local Smoothness
- Blog: Global Convergence in Training Large-Scale Transformers
- Blog: Modeling from Features: a Mean-field Framework for Over-parameterized Deep Neural Networks
- Blog: Error Analysis of Three-Layer Neural Network Trained with PGD for Deep Ritz Method
- Blog: Fast Convergence of Natural Gradient Descent for Over-Parameterized Neural Networks
- Blog: Global Convergence of Deep Networks with One Wide Layer Followed by Pyramidal Topology
- Blog: Foreword: special issue for the journal track of the 11th Asian Conference on Machine Learning (ACML 2019)
- Blog: Gradient Descent Finds Global Minima of Deep Neural Networks
- Blog: Closing the Gap: Achieving Global Convergence (Last Iterate) of Actor-Critic under Markovian Sampling with Neural Network Parametrization
- Blog: Unraveling the Gradient Descent Dynamics of Transformers
- Blog: Benefits of Jointly Training Autoencoders: An Improved Neural Tangent Kernel Analysis
- Blog: A Local Convergence Theory for Mildly Over-Parameterized Two-Layer Neural Network
- Blog: Learning and Generalization in Overparameterized Neural Networks, Going Beyond Two Layers
- Blog: Gradient descent optimizes over-parameterized deep ReLU networks
- Blog: Analyzing Deep PAC-Bayesian Learning with Neural Tangent Kernel: Convergence, Analytic Generalization Bound, and Efficient Hyperparameter Selection
- Blog: Generative Adversarial Imitation Learning with Neural Network Parameterization: Global Optimality and Convergence Rate
- Blog: Non-attracting Regions of Local Minima in Deep and Wide Neural Networks
- Blog: Learning Linear Attention in Polynomial Time
- Blog: A geometric approach of gradient descent algorithms in linear neural networks
- Blog: Mathematical Models of Overparameterized Neural Networks
- Blog: Robust Generalization of Quadratic Neural Networks via Function Identification
- Blog: Global Convergence and Rich Feature Learning in $L$-Layer Infinite-Width Neural Networks under $\mu$ Parametrization
History & citation
Current · Permanent link
- This direction split from Landscape Smoothing through Overparameterization (65% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_over_parameterized_global_convergence_c6d6d653,
title = {over-parameterized global convergence},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/over-parameterized-global-convergence/rdr_c6d6d65353094bbfb306574ae198192b},
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_over_parameterized_global_convergence_c6d6d653_v1,
title = {over-parameterized global convergence},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/over-parameterized-global-convergence/rdr_c6d6d65353094bbfb306574ae198192b/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-20},
}