No article text was recorded for this version.
overparameterization generalization paradox
Version 2 of 21,542 papers2,134 conceptsfrozen 2026-10-04
Papers in this version
- Blog: A Farewell to the Bias-Variance Tradeoff? An Overview of the Theory of Overparameterized Machine Learning
- Blog: Benign, Tempered, or Catastrophic: A Taxonomy of Overfitting
- Blog: A Farewell to the Bias-Variance Tradeoff? An Overview of the Theory of Overparameterized Machine Learning
- Blog: Precise Asymptotic Generalization for Multiclass Classification with Overparameterized Linear Models
- Blog: A Classical View on Benign Overfitting: The Role of Sample Size
- Blog: Generalization Performance of Empirical Risk Minimization on Over-Parameterized Deep ReLU Nets
- Blog: Surprises in high-dimensional ridgeless least squares interpolation
- Blog: Generalization Performance of Empirical Risk Minimization on Over-parameterized Deep ReLU Nets
- Blog: Understanding deep learning requires rethinking generalization
- Blog: Binary Classification of Gaussian Mixtures: Abundance of Support Vectors, Benign Overfitting, and Regularization
- Blog: Generalization Error in Deep Learning
- Blog: Reconciling modern machine learning and the bias-variance trade-off
- Blog: Explaining generalization in deep learning: progress and fundamental limits
- Blog: VC dimension of partially quantized neural networks in the overparametrized regime
- Blog: The generalization error of max-margin linear classifiers: Benign overfitting and high dimensional asymptotics in the overparametrized regime
- Blog: On Uniform Convergence and Low-Norm Interpolation Learning
- Blog: Harmless interpolation of noisy data in regression
- Blog: Double Descent Demystified: Identifying, Interpreting & Ablating the Sources of a Deep Learning Puzzle
- Blog: Double Descent Demystified: Identifying, Interpreting & Ablating the Sources of a Deep Learning Puzzle
- Blog: Benign Overfitting for Regression with Trained Two-Layer ReLU Networks
- Blog: For interpolating kernel machines, minimizing the norm of the ERM solution minimizes stability
- Blog: A Brief Prehistory of Double Descent
- Blog: BENIGN OVERFITTING AND NOISY FEATURES
- Blog: On the proliferation of support vectors in high dimensions
- Blog: On the Generalization Power of Overfitted Two-Layer Neural Tangent Kernel Models
- Blog: On The Power of Deep But Naive Partial Label Learning
- Blog: Overparameterization and Generalization Error: Weighted Trigonometric Interpolation
- Blog: DNN or k-NN: That is the Generalize vs. Memorize Question
- Blog: Generalization Ability of Wide Neural Networks on ℝ
- Blog: Exact Gap between Generalization Error and Uniform Convergence in Random Feature Models
- Blog: Learned Random Label Predictions as a Neural Network Complexity Metric
- Blog: Deep Learning is Not So Mysterious or Different
- Blog: PAC Learnability and Information Bottleneck in Deep Learning: Tutorial and Survey
- Blog: NeurIPS 2020 Competition: Predicting Generalization in Deep Learning
- Blog: Benign Overfitting and Noisy Features
- Blog: Learning ability of interpolating deep convolutional neural networks
- Blog: Theory of Deep Learning III: explaining the non-overfitting puzzle
- Blog: Does data interpolation contradict statistical optimality?
- Blog: A PAC-Bayesian Perspective on the Interpolating Information Criterion
- Blog: The Interpolation Phase Transition in Neural Networks: Memorization and Generalization under Lazy Training
- Blog: Memorize to generalize: on the necessity of interpolation in high dimensional linear regression
- Blog: Double-descent curves in neural networks: a new perspective using Gaussian processes
- Blog: Memorize to Generalize: on the Necessity of Interpolation in High Dimensional Linear Regression
- Blog: Do deep neural networks have an inbuilt Occam's razor?
- Blog: Benign Overfitting and Noisy Features
- Blog: Surprises in High-Dimensional Ridgeless Least Squares Interpolation
- Blog: Provable Tempered Overfitting of Minimal Nets and Typical Nets
- Blog: Theory IIIb: Generalization in Deep Networks
- Blog: SGLD-Based Information Criteria and the Over-Parameterized Regime
- Blog: Precise Asymptotic Generalization for Multiclass Classification with Overparameterized Linear Models
- Blog: Nonasymptotic theory for two-layer neural networks: Beyond the bias-variance trade-off
- Blog: Unveiling Multiple Descents in Unsupervised Autoencoders
- Blog: Redundant representations help generalization in wide neural networks
- Blog: How Linguistics Learned to Stop Worrying and Love the Language Models
- Blog: Just Interpolate: Kernel "Ridgeless" Regression Can Generalize
- Blog: On Computational Entanglement and Its Interpretation in Adversarial Machine Learning
- Blog: Generalizability of Neural Networks Minimizing Empirical Risk Based on Expressive Ability
- Blog: Frivolous Units: Wider Networks Are Not Really That Wide
- Blog: Universal Consistency of Wide and Deep ReLU Neural Networks and Minimax Optimal Convergence Rates for Kolmogorov-Donoho Optimal Function Classes
- Blog: On the proliferation of support vectors in high dimensions*
Showing 60 of 1,542 papers.
History & citation
Current · Permanent link
- Generalization through Minimum Norm Interpolation merged into this direction (71% overlap)
- Information Theoretic Generalization Bounds in Overparameterized Models merged into this direction (54% overlap)
- High Dimensionality as a Requirement for Benign Overfitting merged into this direction (84% overlap)
- Uniform Convergence Restricted to Interpolators merged into this direction (89% overlap)
- Bias and Variance Dynamics in Overparameterized Models merged into this direction (87% overlap)
- The Implicit Bias of Gradient Based Optimization merged into this direction (53% overlap)
- Benign Overfitting in Overparameterized Models merged into this direction (91% overlap)
- Support Vector Proliferation and Criterion Collapse in Overparameterized Models merged into this direction (59% overlap)
- High Dimensional Geometry and Benign Overfitting merged into this direction (59% overlap)
- Fractal Dimension of Stochastic Optimization Trajectories merged into this direction (83% overlap)
- Beyond Geometric Proxies for Neural Network Generalization merged into this direction (62% overlap)
- Width Independent Generalization in Overparameterized Neural Networks merged into this direction (71% overlap)
- Implicit Regularization in Overparameterized Neural Networks merged into this direction (100% overlap)
- Bias and Variance in Overparameterized Interpolation merged into this direction (50% overlap)
- Generalization Beyond the Interpolation Threshold merged into this direction (70% overlap)
- Implicit Regularization in Underparameterized Ridgeless Regression merged into this direction (67% overlap)
- Lipschitz double descent split from this direction (67% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_overparameterization_generalization_para_243df543,
title = {overparameterization generalization paradox},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/overparameterization-generalization-paradox/rdr_243df5439449456bba2812d94a32b3c8},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-22},
}This exact version (version 2, frozen text):
@misc{lacuna_overparameterization_generalization_para_243df543_v2,
title = {overparameterization generalization paradox},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/overparameterization-generalization-paradox/rdr_243df5439449456bba2812d94a32b3c8/v/2},
note = {Version 2, frozen 2026-10-04. Accessed 2026-11-22},
}