{"total":61,"rows":[{"id":"2110.13905","title":"Gradient Descent on Two-layer Nets: Margin Maximization and Simplicity Bias","created":"2021-10-26","cited_by_count":83,"area":null},{"id":"2206.00939","title":"Gradient flow dynamics of shallow ReLU networks for square loss and orthogonal inputs","created":"2022-06-02","cited_by_count":76,"area":null},{"id":"2406.06158","title":"Get rich quick: exact solutions reveal how unbalanced initializations promote rapid feature learning","created":"2024-06-10","cited_by_count":42,"area":null},{"id":"2309.15111","title":"SGD Finds then Tunes Features in Two-Layer Neural Networks with near-Optimal Sample Complexity: A Case Study in the XOR problem","created":"2023-09-26","cited_by_count":39,"area":null},{"id":"2105.11686","title":"Towards Understanding the Condensation of Neural Networks at Initial Training","created":"2021-05-25","cited_by_count":32,"area":null},{"id":"2206.09841","title":"Label noise (stochastic) gradient descent implicitly solves the Lasso for quadratic parametrisation","created":"2022-06-20","cited_by_count":29,"area":null},{"id":"2604.21691","title":"There Will Be a Scientific Theory of Deep Learning","created":"2026-04-23","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":"2207.05952","title":"Implicit regularization of dropout","created":"2022-07-13","cited_by_count":25,"area":null},{"id":"2206.12314","title":"Learning sparse features can lead to overfitting in neural networks","created":"2022-06-24","cited_by_count":23,"area":null},{"id":"2111.15527","title":"Embedding Principle: a hierarchical structure of loss landscape of deep neural networks","created":"2021-11-30","cited_by_count":22,"area":null},{"id":"2205.09072","title":"On the Effective Number of Linear Regions in Shallow Univariate ReLU Networks: Convergence Guarantees and Implicit Bias","created":"2022-05-18","cited_by_count":21,"area":null},{"id":"2209.07263","title":"Robustness in deep learning: The good (width), the bad (depth), and the ugly (initialization)","created":"2022-09-15","cited_by_count":18,"area":null},{"id":"2205.12101","title":"Empirical Phase Diagram for Three-layer Neural Networks with Infinite Width","created":"2022-05-24","cited_by_count":17,"area":null},{"id":"2504.09484","title":"An overview of condensation phenomenon in deep learning","created":"2025-04-13","cited_by_count":17,"area":null},{"id":"2303.06561","title":"Phase Diagram of Initial Condensation for Two-layer Neural Networks","created":"2023-03-12","cited_by_count":16,"area":null},{"id":"2305.12133","title":"Loss Spike in Training Neural Networks","created":"2023-05-20","cited_by_count":16,"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":"2305.12467","title":"Understanding Multi-phase Optimization Dynamics and Rich Nonlinear Behaviors of ReLU Networks","created":"2023-05-21","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":"2506.06489","title":"Alternating Gradient Flows: A Theory of Feature Learning in Two-layer Neural Networks","created":"2025-06-06","cited_by_count":14,"area":null},{"id":"2111.02278","title":"Mean-field Analysis of Piecewise Linear Solutions for Wide ReLU Networks","created":"2021-11-03","cited_by_count":13,"area":null},{"id":"2107.04479","title":"Convergence analysis for gradient flows in the training of artificial neural networks with ReLU activation","created":"2021-07-09","cited_by_count":11,"area":null},{"id":"2110.06488","title":"The Convex Geometry of Backpropagation: Neural Network Gradient Flows Converge to Extreme Points of the Dual Convex Program","created":"2021-10-13","cited_by_count":11,"area":null},{"id":"2410.02348","title":"Simplicity bias and optimization threshold in two-layer ReLU networks","created":"2024-10-03","cited_by_count":11,"area":null},{"id":"2503.03595","title":"Towards Understanding Text Hallucination of Diffusion Models via Local Generation Bias","created":"2025-03-05","cited_by_count":11,"area":"diffusion"},{"id":"2603.00742","title":"To Use or not to Use Muon: How Simplicity Bias in Optimizers Matters","created":"2026-02-28","cited_by_count":10,"area":null},{"id":"2309.12642","title":"RHINO: Regularizing the Hash-based Implicit Neural Representation","created":"2023-09-22","cited_by_count":9,"area":null},{"id":"2411.08798","title":"Learning Gaussian Multi-Index Models with Gradient Flow: Time Complexity and Directional Convergence","created":"2024-11-13","cited_by_count":9,"area":null},{"id":"2412.18283","title":"On the Local Complexity of Linear Regions in Deep ReLU Networks","created":"2024-12-24","cited_by_count":9,"area":null},{"id":"2305.09947","title":"Understanding the Initial Condensation of Convolutional Neural Networks","created":"2023-05-17","cited_by_count":8,"area":null},{"id":"2602.06801","title":"On the Non-Identifiability of Steering Vectors in Large Language Models","created":"2026-02-06","cited_by_count":8,"area":"mechinterp"},{"id":"2211.11623","title":"Linear Stability Hypothesis and Rank Stratification for Nonlinear Models","created":"2022-11-21","cited_by_count":7,"area":null},{"id":"2403.08121","title":"Early Directional Convergence in Deep Homogeneous Neural Networks for Small Initializations","created":"2024-03-12","cited_by_count":7,"area":null},{"id":"2202.00790","title":"On Regularizing Coordinate-MLPs","created":"2022-02-01","cited_by_count":5,"area":null},{"id":"2206.05317","title":"Intrinsic dimensionality and generalization properties of the $\\mathcal{R}$-norm inductive bias","created":"2022-06-10","cited_by_count":5,"area":null},{"id":"2209.13394","title":"Magnitude and Angle Dynamics in Training Single ReLU Neurons","created":"2022-09-27","cited_by_count":5,"area":null},{"id":"2307.08921","title":"Optimistic Estimate Uncovers the Potential of Nonlinear Models","created":"2023-07-18","cited_by_count":5,"area":null},{"id":"2405.15942","title":"Can Implicit Bias Imply Adversarial Robustness?","created":"2024-05-24","cited_by_count":5,"area":null},{"id":"2410.08309","title":"Swing-by Dynamics in Concept Learning and Compositional Generalization","created":"2024-10-10","cited_by_count":5,"area":"diffusion"},{"id":"2406.12615","title":"When Are Bias-Free ReLU Networks Effectively Linear Networks?","created":"2024-06-18","cited_by_count":4,"area":null},{"id":"2510.09816","title":"A mathematical theory for understanding when abstract representations emerge in neural networks","created":"2025-10-10","cited_by_count":4,"area":null},{"id":"2402.15958","title":"On the dynamics of three-layer neural networks: initial condensation","created":"2024-02-25","cited_by_count":3,"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":"2510.21078","title":"Neural Collapse under Gradient Flow on Shallow ReLU Networks for Orthogonally Separable Data","created":"2025-10-24","cited_by_count":2,"area":null},{"id":"2607.03613","title":"Implicit Bias of SGD in Multivariate ReLU Networks: Effective Width Collapse","created":"2026-07-03","cited_by_count":2,"area":null},{"id":"2103.12499","title":"Initializing ReLU networks in an expressive subspace of weights","created":"2021-03-23","cited_by_count":1,"area":null},{"id":"2401.03824","title":"A topological description of loss surfaces based on Betti Numbers","created":"2024-01-08","cited_by_count":1,"area":null},{"id":"2505.22578","title":"Favorability of Loss Landscape with Weight Decay Requires Both Large Overparametrization and Initialization","created":"2025-05-28","cited_by_count":1,"area":null},{"id":"2603.17785","title":"A Dual Certificate Approach to Sparsity in Infinite-Width Shallow Neural Networks","created":"2026-03-18","cited_by_count":1,"area":null},{"id":"2404.04859","title":"Demystifying Lazy Training of Neural Networks from a Macroscopic Viewpoint","created":"2024-04-07","cited_by_count":0,"area":null},{"id":"2406.18035","title":"Local Linear Recovery Guarantee of Deep Neural Networks at Overparameterization","created":"2024-06-26","cited_by_count":0,"area":null},{"id":"2503.10587","title":"The Spectral Bias of Shallow Neural Network Learning is Shaped by the Choice of Non-linearity","created":"2025-03-13","cited_by_count":0,"area":null},{"id":"2505.17919","title":"KITINet: KInetic Theory Inspired Inter-Channel Information Exchange for Residual Networks","created":"2025-05-23","cited_by_count":0,"area":null},{"id":"2512.21447","title":"An Equivariance Toolbox for Learning Dynamics","created":"2025-12-24","cited_by_count":0,"area":null},{"id":"2602.00827","title":"Over-Alignment vs Over-Fitting: The Role of Feature Learning Strength in Generalization","created":"2026-01-31","cited_by_count":0,"area":null},{"id":"2603.10397","title":"On the Learning Dynamics of Two-layer Linear Networks with Label Noise SGD","created":"2026-03-11","cited_by_count":0,"area":null},{"id":"2605.27097","title":"Mildly Overparameterized ReLU Networks on Orthogonal Data: Incremental Learning and Implicit Bias","created":"2026-05-26","cited_by_count":0,"area":null},{"id":"2609.39408","title":"Awakening of the Buddha: Subspace Learning During Population-Loss Plateaus","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.04533","title":"Weight Decay and Neuron Condensation: A Three-Stage Analysis of Two-Layer ReLU Networks","created":"2026-10-03","cited_by_count":0,"area":null},{"id":"2610.11475","title":"Rare Gate Disagreements Can Limit Plasticity: When Gradient Flow Mispredicts Finite-Batch SGD","created":"2026-10-08","cited_by_count":0,"area":null}],"next_cursor":null}