{"total":21,"rows":[{"id":"2303.06173","title":"Unifying Grokking and Double Descent","created":"2023-03-10","cited_by_count":50,"area":null},{"id":"2112.03215","title":"Multi-scale Feature Learning Dynamics: Insights for Double Descent","created":"2021-12-06","cited_by_count":24,"area":null},{"id":"2303.01475","title":"Over-training with Mixup May Hurt Generalization","created":"2023-03-02","cited_by_count":13,"area":null},{"id":"2206.00501","title":"Benign Overfitting in Classification: Provably Counter Label Noise with Larger Models","created":"2022-06-01","cited_by_count":5,"area":null},{"id":"2409.05782","title":"Unified Neural Network Scaling Laws and Scale-time Equivalence","created":"2024-09-09","cited_by_count":4,"area":null},{"id":"2407.09845","title":"Towards Understanding Epoch-wise Double descent in Two-layer Linear Neural Networks","created":"2024-07-13","cited_by_count":3,"area":null},{"id":"2310.11077","title":"United We Stand: Using Epoch-wise Agreement of Ensembles to Combat Overfit","created":"2023-10-17","cited_by_count":2,"area":null},{"id":"2412.12968","title":"On Local Overfitting and Forgetting in Deep Neural Networks","created":"2024-12-17","cited_by_count":2,"area":null},{"id":"2505.01751","title":"A dynamic view of some anomalous phenomena in SGD","created":"2025-05-03","cited_by_count":2,"area":null},{"id":"2509.01397","title":"Double Descent and Overparameterization in Particle Physics Data","created":"2025-09-01","cited_by_count":2,"area":null},{"id":"2605.27078","title":"Two Speeds of Learning: A Representation-Readout Decomposition of Grokking and Double Descent","created":"2026-05-26","cited_by_count":2,"area":null},{"id":"2409.06830","title":"Noisy Early Stopping for Noisy Labels","created":"2024-09-10","cited_by_count":1,"area":null},{"id":"2201.11939","title":"With Greater Distance Comes Worse Performance: On the Perspective of Layer Utilization and Model Generalization","created":"2022-01-28","cited_by_count":0,"area":null},{"id":"2305.15907","title":"Double Descent of Discrepancy: A Task-, Data-, and Model-Agnostic Phenomenon","created":"2023-05-25","cited_by_count":0,"area":null},{"id":"2310.11094","title":"Relearning Forgotten Knowledge: on Forgetting, Overfit and Training-Free Ensembles of DNNs","created":"2023-10-17","cited_by_count":0,"area":null},{"id":"2311.01442","title":"Deep Double Descent for Time Series Forecasting: Avoiding Undertrained Models","created":"2023-11-02","cited_by_count":0,"area":null},{"id":"2411.02184","title":"Double Descent Meets Out-of-Distribution Detection: Theoretical Insights and Empirical Analysis on the role of model complexity","created":"2024-11-04","cited_by_count":0,"area":null},{"id":"2503.02302","title":"On the Relationship Between Double Descent of CNNs and Shape/Texture Bias Under Learning Process","created":"2025-03-04","cited_by_count":0,"area":null},{"id":"2507.08686","title":"Forget Me Not: Fighting Local Overfitting with Knowledge Fusion and Distillation","created":"2025-07-11","cited_by_count":0,"area":null},{"id":"2601.08316","title":"Deep Exploration of Epoch-wise Double Descent in Noisy Data: Signal Separation, Large Activation, and Benign Overfitting","created":"2026-01-13","cited_by_count":0,"area":null},{"id":"2608.24210","title":"A Data-dependent Early Stopping Rule using Rademacher Complexity with L1-norm","created":"2026-08-25","cited_by_count":0,"area":null}],"next_cursor":null}