Generalization Analysis of Online Stochastic Gradient Descent for Overparameterized Two-Layer Neural Networks

arXiv:2407.07670 · stat.ML, cs.LG · Submitted 2024-07-10 · Read on arXiv

stat.ML, cs.LG

Submitted: 2024-07-10

Updated: 2026-09-24

Terminology

• Generalization — 12× in this paper · explained in 13 episodes
• Activation Function — 8× in this paper · explained in 1 episode
• Consistency — 8× in this paper · explained in 3 episodes
• Error Decomposition — 8× in this paper · explained in 3 episodes
• Neural Tangent Kernel — 8× in this paper
• Regularization — 8× in this paper · explained in 3 episodes
• Loss Function — 7× in this paper · explained in 2 episodes
• Hilbert Space — 6× in this paper · explained in 2 episodes
• Objective Function — 4× in this paper · explained in 2 episodes
• Reproducing Kernel Hilbert Space — 3× in this paper
• Reproducing Kernel Hilbert Space (RKHS) — 2× in this paper · explained in 3 episodes
• Stochastic Gradient Descent (SGD) — 2× in this paper · explained in 5 episodes
• Differentially Private — 1× in this paper · explained in 3 episodes
• Generalization Bounds — 1× in this paper · explained in 2 episodes
• Trace — 1× in this paper · explained in 2 episodes
• Transformer — 1× in this paper · explained in 2 episodes

Sources

• Making Gradient Descent Optimal for Strongly Convex Stochastic Optimization
• Stochastic Gradient Descent for Operator Learning in Hilbert Spaces: Convergence Rates and Minimax Lower Bounds

Related papers

• Behavior of prediction performance metrics with rare events
• Optimal Estimation of Generic Dynamics by Path-Dependent Neural Jump ODEs
• A Posterior-Dynamics Framework for Imaging Inverse Problems with Pretrained Diffusion Priors
• One Permutation Is All You Need: Fast, Deterministic Feature Importance and Model Stress-Testing
• Online Conformal Prediction for Non-Exchangeable Panel Data
• Deep Time-Series Forecasting in 10 Years: A Survey