{"total":46,"rows":[{"id":"2306.07042","title":"Transformers learn through gradual rank increase","created":"2023-06-12","cited_by_count":52,"area":null},{"id":"2403.02241","title":"Neural Redshift: Random Networks are not Random Functions","created":"2024-03-04","cited_by_count":43,"area":null},{"id":"2406.10650","title":"The Implicit Bias of Adam on Separable Data","created":"2024-06-15","cited_by_count":36,"area":null},{"id":"2310.02541","title":"Benign Overfitting and Grokking in ReLU Networks for XOR Cluster Data","created":"2023-10-04","cited_by_count":33,"area":null},{"id":"2311.07568","title":"Feature emergence via margin maximization: case studies in algebraic tasks","created":"2023-11-13","cited_by_count":33,"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":"2408.11804","title":"Approaching Deep Learning through the Spectral Dynamics of Weights","created":"2024-08-21","cited_by_count":31,"area":null},{"id":"2303.01462","title":"Benign Overfitting in Linear Classifiers and Leaky ReLU Networks from KKT Conditions for Margin Maximization","created":"2023-03-02","cited_by_count":29,"area":null},{"id":"2307.12851","title":"Early Neuron Alignment in Two-layer ReLU Networks with Small Initialization","created":"2023-07-24","cited_by_count":28,"area":null},{"id":"2302.00457","title":"Simplicity Bias in 1-Hidden Layer Neural Networks","created":"2023-02-01","cited_by_count":26,"area":null},{"id":"2303.01456","title":"The Double-Edged Sword of Implicit Bias: Generalization vs. Robustness in ReLU Networks","created":"2023-03-02","cited_by_count":23,"area":null},{"id":"2302.09235","title":"Generalization and Stability of Interpolating Neural Networks with Minimal Width","created":"2023-02-18","cited_by_count":21,"area":null},{"id":"2310.18935","title":"Implicit Bias of Gradient Descent for Two-layer ReLU and Leaky ReLU Networks on Nearly-orthogonal Data","created":"2023-10-29","cited_by_count":18,"area":null},{"id":"2310.01687","title":"From Stability to Chaos: Analyzing Gradient Descent Dynamics in Quadratic Regression","created":"2023-10-02","cited_by_count":17,"area":null},{"id":"2306.06479","title":"Learning a Neuron by a Shallow ReLU Network: Dynamics and Implicit Bias for Correlated Inputs","created":"2023-06-10","cited_by_count":16,"area":null},{"id":"2410.01774","title":"Trained Transformer Classifiers Generalize and Exhibit Benign Overfitting In-Context","created":"2024-10-02","cited_by_count":15,"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":"2310.12408","title":"Provable Guarantees for Neural Networks via Gradient Feature Learning","created":"2023-10-19","cited_by_count":14,"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":"2410.14581","title":"Optimizing Attention with Mirror Descent: Generalized Max-Margin Token Selection","created":"2024-10-18","cited_by_count":9,"area":null},{"id":"2211.06077","title":"Overparameterized random feature regression with nearly orthogonal data","created":"2022-11-11","cited_by_count":7,"area":null},{"id":"2405.15942","title":"Can Implicit Bias Imply Adversarial Robustness?","created":"2024-05-24","cited_by_count":5,"area":null},{"id":"2502.17340","title":"Low-rank bias, weight decay, and model merging in neural networks","created":"2025-02-24","cited_by_count":5,"area":null},{"id":"2302.00257","title":"Implicit Regularization Leads to Benign Overfitting for Sparse Linear Regression","created":"2023-02-01","cited_by_count":4,"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":"2510.01303","title":"Low Rank Gradients and Where to Find Them","created":"2025-10-01","cited_by_count":4,"area":null},{"id":"2307.09193","title":"ESMC: Entire Space Multi-Task Model for Post-Click Conversion Rate via Parameter Constraint","created":"2023-07-18","cited_by_count":3,"area":null},{"id":"2308.03215","title":"The Effect of SGD Batch Size on Autoencoder Learning: Sparsity, Sharpness, and Feature Learning","created":"2023-08-06","cited_by_count":2,"area":null},{"id":"2312.04752","title":"A Test-Time Learning Approach to Reparameterize the Geophysical Inverse Problem with a Convolutional Neural Network","created":"2023-12-07","cited_by_count":2,"area":null},{"id":"2402.10470","title":"Theoretical Understanding of Learning from Adversarial Perturbations","created":"2024-02-16","cited_by_count":2,"area":null},{"id":"2502.16977","title":"Convergence of Shallow ReLU Networks on Weakly Interacting Data","created":"2025-02-24","cited_by_count":2,"area":null},{"id":"2503.17503","title":"Towards Understanding the Benefits of Neural Network Parameterizations in Geophysical Inversions: A Study With Neural Fields","created":"2025-03-21","cited_by_count":2,"area":null},{"id":"2306.01870","title":"Implicit Regularization in Feedback Alignment Learning Mechanisms for Neural Networks","created":"2023-06-02","cited_by_count":1,"area":null},{"id":"2508.15086","title":"Wormhole Dynamics in Deep Neural Networks","created":"2025-08-20","cited_by_count":1,"area":null},{"id":"2602.13910","title":"Sufficient Conditions for Stability of Minimum-Norm Interpolating Deep ReLU Networks","created":"2026-02-14","cited_by_count":1,"area":null},{"id":"2305.15203","title":"Frequency maps reveal the correlation between Adversarial Attacks and Implicit Bias","created":"2023-05-24","cited_by_count":0,"area":null},{"id":"2305.15276","title":"Sparse Mean Estimation in Adversarial Settings via Incremental Learning","created":"2023-05-24","cited_by_count":0,"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},{"id":"2603.02095","title":"On the Rate of Convergence of GD in Non-linear Neural Networks: An Adversarial Robustness Perspective","created":"2026-03-02","cited_by_count":0,"area":null}],"next_cursor":null}