No article text was recorded for this version.
optimization-generalization gap
Version 1 of 128 papers28 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Enumerate Lasso Solutions for Feature Selection
- Blog: Nonparametric Classification on Low Dimensional Manifolds using Overparameterized Convolutional Residual Networks
- Blog: Learning a hyperplane classifier by minimizing an exact bound on the VC dimension
- Blog: The loss surface and expressivity of deep convolutional neural networks
- Blog: Generalization Bounds for Stochastic Gradient Descent via Localized $\varepsilon$-Covers
- Blog: Understanding the Loss Surface of Neural Networks for Binary Classification
- Blog: MoXCo: How I learned to stop exploring and love my local minima?
- Blog: Optimization, Generalization and Differential Privacy Bounds for Gradient Descent on Kolmogorov–Arnold Networks
- Blog: On global convergence of ResNets: From finite to infinite width using linear parameterization
- Blog: Disentangling Trainability and Generalization in Deep Neural Networks
- Blog: ALRMR-GEC: Adjusting Learning Rate Based on Memory Rate to Optimize the Edit Scorer for Grammatical Error Correction
- Blog: SGD Converges to Global Minimum in Deep Learning via Star-convex Path
- Blog: A Recipe for Global Convergence Guarantee in Deep Neural Networks
- Blog: Global Convergence of Over-parameterized Deep Equilibrium Models
- Blog: Neural Network Weights Do Not Converge to Stationary Points: An Invariant Measure Perspective
- Blog: K-SAM: Sharpness-Aware Minimization at the Speed of SGD
- Blog: Global Convergence in Training Large-Scale Transformers
- Blog: Adding One Neuron Can Eliminate All Bad Local Minima
- Blog: Modeling from Features: a Mean-field Framework for Over-parameterized Deep Neural Networks
- Blog: Nearly-tight Bounds for Deep Kernel Learning
- Blog: Benign Underfitting of Stochastic Gradient Descent
- Blog: Effect of Depth and Width on Local Minima in Deep Learning
- Blog: Global Convergence of Deep Networks with One Wide Layer Followed by Pyramidal Topology
- Blog: Gradient Descent Finds Global Minima of Deep Neural Networks
- Blog: Topology and Geometry of Half-Rectified Network Optimization
- Blog: Select without Fear: Almost All Minibatch Schedules Generalize Optimally
- Blog: Sketched Ridge Regression: Optimization Perspective, Statistical Perspective, and Model Averaging
- Blog: Generalization bound of globally optimal non-convex neural network training: Transportation map estimation by infinite dimensional Langevin dynamics
History & citation
Current · Permanent link
- This direction split from The Disconnect Between Optimization Success and Generalization (86% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_optimization_generalization_gap_f9a7a480,
title = {optimization-generalization gap},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/optimization-generalization-gap/rdr_f9a7a4807a644e309f15bb6ad8823d3a},
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_optimization_generalization_gap_f9a7a480_v1,
title = {optimization-generalization gap},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/optimization-generalization-gap/rdr_f9a7a4807a644e309f15bb6ad8823d3a/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-20},
}