generalization error

MMIM: An Interpretable Regularization Method for Neural Networks (Student Abstract) AAAI 2021 Model Performance Scaling with Multiple Data Sources ICML 2021 Model, sample, and epoch-wise descents: exact solution of gradient flow in the random feature model NeurIPS 2021 Never Go Full Batch (in Stochastic Convex Optimization) NeurIPS 2021 On Linear Stability of SGD and Input-Smoothness of Neural Networks NeurIPS 2021 On the Algorithmic Stability of Adversarial Training NeurIPS 2021 On the Generalization Power of Overfitted Two-Layer Neural Tangent Kernel Models ICML 2021 On the Inherent Regularization Effects of Noise Injection During Training ICML 2021 On the Role of Optimization in Double Descent: A Least Squares Study NeurIPS 2021 On the Universality of the Double Descent Peak in Ridgeless Regression ICLR 2021 SGD Generalizes Better Than GD (And Regularization Doesn’t Help) COLT 2021 Single Layer Predictive Normalized Maximum Likelihood for Out-of-Distribution Detection NeurIPS 2021 Statistical mechanical analysis of neural network pruning UAI 2021 The curious case of adversarially robust models: More data can help, double descend, or hurt generalization UAI 2021 Towards Open-World Feature Extrapolation: An Inductive Graph Learning Approach NeurIPS 2021 Towards Understanding Why Lookahead Generalizes Better Than SGD and Beyond NeurIPS 2021 Training Data Subset Selection for Regression with Controlled Generalization Error ICML 2021 What Causes the Test Error? Going Beyond Bias-Variance via ANOVA JMLR 2021 Why Lottery Ticket Wins? A Theoretical Perspective of Sample Complexity on Sparse Neural Networks NeurIPS 2021 A Constructive Prediction of the Generalization Error Across Scales ICLR 2020 Adaptive Approximation and Generalization of Deep Neural Network with Intrinsic Dimensionality JMLR 2020 Adaptive Region-Based Active Learning ICML 2020 A Dynamical Central Limit Theorem for Shallow Neural Networks NeurIPS 2020 A Generalized Neural Tangent Kernel Analysis for Two-layer Neural Networks NeurIPS 2020 Dataless Model Selection With the Deep Frame Potential CVPR 2020