{"total":22,"rows":[{"id":"2205.10343","title":"Towards Understanding Grokking: An Effective Theory of Representation Learning","created":"2022-05-20","cited_by_count":230,"area":null},{"id":"2303.06173","title":"Unifying Grokking and Double Descent","created":"2023-03-10","cited_by_count":50,"area":null},{"id":"2405.20233","title":"Grokfast: Accelerated Grokking by Amplifying Slow Gradients","created":"2024-05-30","cited_by_count":41,"area":null},{"id":"2306.13253","title":"Predicting Grokking Long Before it Happens: A look into the loss landscape of models which grok","created":"2023-06-23","cited_by_count":35,"area":null},{"id":"2308.12553","title":"Don't blame Dataset Shift! Shortcut Learning due to Gradients and Cross Entropy","created":"2023-08-24","cited_by_count":30,"area":null},{"id":"2210.15435","title":"Grokking phase transitions in learning local rules with gradient descent","created":"2022-10-26","cited_by_count":28,"area":null},{"id":"2303.01475","title":"Over-training with Mixup May Hurt Generalization","created":"2023-03-02","cited_by_count":13,"area":null},{"id":"2502.00620","title":"Representations Shape Weak-to-Strong Generalization: Theoretical Insights and Empirical Predictions","created":"2025-02-02","cited_by_count":10,"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":"2410.11985","title":"The Fair Language Model Paradox","created":"2024-10-15","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":"2505.01751","title":"A dynamic view of some anomalous phenomena in SGD","created":"2025-05-03","cited_by_count":2,"area":null},{"id":"2507.17748","title":"Large Learning Rates Simultaneously Achieve Robustness to Spurious Correlations and Compressibility","created":"2025-07-23","cited_by_count":2,"area":null},{"id":"2207.12547","title":"The BUTTER Zone: An Empirical Study of Training Dynamics in Fully Connected Neural Networks","created":"2022-07-25","cited_by_count":1,"area":null},{"id":"2303.07925","title":"Deep incremental learning models for financial temporal tabular datasets with distribution shifts","created":"2023-03-14","cited_by_count":1,"area":null},{"id":"2309.01694","title":"No Data Augmentation? Alternative Regularizations for Effective Training on Small Datasets","created":"2023-09-04","cited_by_count":1,"area":null},{"id":"2201.12803","title":"Generalizing similarity in noisy setups: the DIBS phenomenon","created":"2022-01-30","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":"2507.01414","title":"Decomposing Prediction Mechanisms for In-Context Recall","created":"2025-07-02","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":"2604.09716","title":"Training Deep Visual Networks Beyond Loss and Accuracy Through a Dynamical Systems Approach","created":"2026-04-08","cited_by_count":0,"area":null},{"id":"2604.21546","title":"Component-Based Out-of-Distribution Detection","created":"2026-04-23","cited_by_count":0,"area":null}],"next_cursor":null}