{"total":18,"rows":[{"id":"2406.10650","title":"The Implicit Bias of Adam on Separable Data","created":"2024-06-15","cited_by_count":36,"area":null},{"id":"2506.13018","title":"Symmetry in Neural Network Parameter Spaces","created":"2025-06-16","cited_by_count":36,"area":null},{"id":"2402.05738","title":"Implicit Bias and Fast Convergence Rates for Self-attention","created":"2024-02-08","cited_by_count":31,"area":null},{"id":"2512.20607","title":"Saddle-to-Saddle Dynamics Explains A Simplicity Bias Across Neural Network Architectures","created":"2025-12-23","cited_by_count":15,"area":null},{"id":"2403.06925","title":"Transformers Learn Low Sensitivity Functions: Investigations and Implications","created":"2024-03-11","cited_by_count":14,"area":null},{"id":"2409.17335","title":"Non-asymptotic Convergence of Training Transformers for Next-token Prediction","created":"2024-09-25","cited_by_count":13,"area":null},{"id":"2505.24022","title":"The Rich and the Simple: On the Implicit Bias of Adam and SGD","created":"2025-05-29","cited_by_count":13,"area":null},{"id":"2405.17299","title":"Simplicity Bias of Two-Layer Networks beyond Linearly Separable Data","created":"2024-05-27","cited_by_count":11,"area":null},{"id":"2505.00926","title":"How Transformers Learn Regular Language Recognition: A Theoretical Study on Training Dynamics and Implicit Bias","created":"2025-05-02","cited_by_count":11,"area":null},{"id":"2406.03944","title":"Provably Neural Active Learning Succeeds via Prioritizing Perplexing Samples","created":"2024-06-06","cited_by_count":5,"area":null},{"id":"2406.12615","title":"When Are Bias-Free ReLU Networks Effectively Linear Networks?","created":"2024-06-18","cited_by_count":4,"area":null},{"id":"2410.23672","title":"Provable Benefit of Cutout and CutMix for Feature Learning","created":"2024-10-31","cited_by_count":4,"area":null},{"id":"2511.22270","title":"Towards Understanding Generalization in DP-GD: A Case Study in Training Two-Layer CNNs","created":"2025-11-27","cited_by_count":4,"area":null},{"id":"2412.07971","title":"Effectiveness of Distributed Gradient Descent with Local Steps for Overparameterized Models","created":"2024-12-10","cited_by_count":1,"area":null},{"id":"2606.05863","title":"Deciphering Two Training Clocks in Grokking via Deep Linear Network Theory with Conditional ReLU Reduction","created":"2026-06-04","cited_by_count":1,"area":null},{"id":"2504.08628","title":"Gradient Descent Robustly Learns the Intrinsic Dimension of Data in Training Convolutional Neural Networks","created":"2025-04-11","cited_by_count":0,"area":null},{"id":"2505.16204","title":"Directional Convergence, Benign Overfitting of Gradient Descent in leaky ReLU two-layer Neural Networks","created":"2025-05-22","cited_by_count":0,"area":null},{"id":"2602.06208","title":"Emergent Low-Rank Training Dynamics in MLPs with Smooth Activations","created":"2026-02-05","cited_by_count":0,"area":null}],"next_cursor":null}