{"total":76,"rows":[{"id":"2209.04836","title":"Git Re-Basin: Merging Models modulo Permutation Symmetries","created":"2022-09-11","cited_by_count":471,"area":null},{"id":"2208.12591","title":"On the Implicit Bias in Deep-Learning Algorithms","created":"2022-08-26","cited_by_count":86,"area":null},{"id":"2210.05337","title":"SGD with Large Step Sizes Learns Sparse Features","created":"2022-10-11","cited_by_count":68,"area":null},{"id":"2305.18270","title":"How Two-Layer Neural Networks Learn, One (Giant) Step at a Time","created":"2023-05-29","cited_by_count":68,"area":null},{"id":"2304.00488","title":"Saddle-to-Saddle Dynamics in Diagonal Linear Networks","created":"2023-04-02","cited_by_count":57,"area":null},{"id":"2306.07042","title":"Transformers learn through gradual rank increase","created":"2023-06-12","cited_by_count":52,"area":null},{"id":"2210.07082","title":"Implicit Bias in Leaky ReLU Networks Trained on High-Dimensional Data","created":"2022-10-13","cited_by_count":46,"area":null},{"id":"2302.05882","title":"From high-dimensional & mean-field dynamics to dimensionless ODEs: A unifying approach to SGD in two-layers networks","created":"2023-02-12","cited_by_count":43,"area":null},{"id":"2301.11500","title":"Understanding Incremental Learning of Gradient Descent: A Fine-grained Analysis of Matrix Sensing","created":"2023-01-27","cited_by_count":42,"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":"2211.05641","title":"Regression as Classification: Influence of Task Formulation on Neural Network Features","created":"2022-11-10","cited_by_count":29,"area":null},{"id":"2208.14673","title":"Incremental Learning in Diagonal Linear Networks","created":"2022-08-31","cited_by_count":28,"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":"2302.10034","title":"Over-Parameterization Exponentially Slows Down Gradient Descent for Learning a Single Neuron","created":"2023-02-20","cited_by_count":25,"area":null},{"id":"2410.19637","title":"A distributional simplicity bias in the learning dynamics of transformers","created":"2024-10-25","cited_by_count":24,"area":null},{"id":"2309.01213","title":"Implicit regularization of deep residual networks towards neural ODEs","created":"2023-09-03","cited_by_count":20,"area":null},{"id":"2303.01353","title":"Penalising the biases in norm regularisation enforces sparsity","created":"2023-03-02","cited_by_count":19,"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":"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":"2508.12837","title":"Learning In-context n-grams with Transformers: Sub-n-grams Are Near-stationary Points","created":"2025-08-18","cited_by_count":16,"area":null},{"id":"2305.18502","title":"Escaping mediocrity: how two-layer networks learn hard generalized linear models with SGD","created":"2023-05-29","cited_by_count":15,"area":null},{"id":"2402.19262","title":"Masks, Signs, And Learning Rate Rewinding","created":"2024-02-29","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":"2404.08602","title":"Sliding down the stairs: how correlated latent variables accelerate learning with neural networks","created":"2024-04-12","cited_by_count":12,"area":null},{"id":"2402.09226","title":"Directional Convergence Near Small Initializations and Saddles in Two-Homogeneous Neural Networks","created":"2024-02-14","cited_by_count":11,"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":"2410.02348","title":"Simplicity bias and optimization threshold in two-layer ReLU networks","created":"2024-10-03","cited_by_count":11,"area":null},{"id":"2310.02396","title":"Inductive biases of multi-task learning and finetuning: multiple regimes of feature reuse","created":"2023-10-03","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":"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":"2404.12293","title":"Singular-limit analysis of gradient descent with noise injection","created":"2024-04-18","cited_by_count":7,"area":null},{"id":"2507.07207","title":"Scaling can lead to compositional generalization","created":"2025-07-09","cited_by_count":7,"area":null},{"id":"2509.25351","title":"Gradient Descent with Large Step Sizes: Chaos and Fractal Convergence Region","created":"2025-09-29","cited_by_count":7,"area":null},{"id":"2302.02904","title":"Rethinking Gauss-Newton for learning over-parameterized models","created":"2023-02-06","cited_by_count":6,"area":null},{"id":"2402.05626","title":"Loss Landscape of Shallow ReLU-like Neural Networks: Stationary Points, Saddle Escape, and Network Embedding","created":"2024-02-08","cited_by_count":6,"area":null},{"id":"2410.14837","title":"Topological obstruction to the training of shallow ReLU neural networks","created":"2024-10-18","cited_by_count":6,"area":null},{"id":"2506.19031","title":"When Diffusion Models Memorize: Inductive Biases in Probability Flow of Minimum-Norm Shallow Neural Nets","created":"2025-06-23","cited_by_count":6,"area":"diffusion"},{"id":"2602.00693","title":"Topology and Geometry of the Learning Space of ReLU Networks: Connectivity and Singularities","created":"2026-01-31","cited_by_count":6,"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":"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":"2406.12615","title":"When Are Bias-Free ReLU Networks Effectively Linear Networks?","created":"2024-06-18","cited_by_count":4,"area":null},{"id":"2407.20724","title":"Exploring Loss Landscapes through the Lens of Spin Glass Theory","created":"2024-07-30","cited_by_count":4,"area":null},{"id":"2505.21722","title":"Saddle-To-Saddle Dynamics in Deep ReLU Networks: Low-Rank Bias in the First Saddle Escape","created":"2025-05-27","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":"2603.02064","title":"Never Saddle for Reparameterized Steepest Descent as Mirror Flow","created":"2026-03-02","cited_by_count":4,"area":null},{"id":"2303.17805","title":"On the Effect of Initialization: The Scaling Path of 2-Layer Neural Networks","created":"2023-03-31","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":"2502.02996","title":"Building Bridges between Regression, Clustering, and Classification","created":"2025-02-05","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":"2508.00127","title":"Structured Transformations for Stable and Interpretable Neural Computation","created":"2025-07-31","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":"2601.22563","title":"EUGens: Efficient, Unified, and General Dense Layers","created":"2026-01-30","cited_by_count":2,"area":null},{"id":"2602.19143","title":"Incremental Learning of Sparse Attention Patterns in Transformers","created":"2026-02-22","cited_by_count":2,"area":null},{"id":"2604.09412","title":"Sharp description of local minima in the loss landscape of high-dimensional two-layer ReLU neural networks","created":"2026-04-10","cited_by_count":2,"area":"distill"},{"id":"2606.23198","title":"Incremental Learning in Mirror Flows","created":"2026-06-22","cited_by_count":2,"area":null},{"id":"2210.13879","title":"Proximal Mean Field Learning in Shallow Neural Networks","created":"2022-10-25","cited_by_count":1,"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":"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":"2508.02126","title":"Understanding Learning Dynamics Through Structured Representations","created":"2025-08-04","cited_by_count":1,"area":null},{"id":"2601.07830","title":"Optimal Learning Rate Schedule for Balancing Effort and Performance","created":"2026-01-12","cited_by_count":1,"area":null},{"id":"2607.12332","title":"Gradient Flow Dynamics and Implicit Bias of Diagonal Linear Networks under Infinitesimal Initialization","created":"2026-07-14","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":"2407.05494","title":"Prospective Messaging: Learning in Networks with Communication Delays","created":"2024-07-07","cited_by_count":0,"area":null},{"id":"2410.09771","title":"EUGens: Efficient, Unified, and General Dense Layers","created":"2024-10-13","cited_by_count":0,"area":null},{"id":"2509.23887","title":"Gradient Flow Convergence Guarantee for General Neural Network Architectures","created":"2025-09-28","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":"2602.06208","title":"Emergent Low-Rank Training Dynamics in MLPs with Smooth Activations","created":"2026-02-05","cited_by_count":0,"area":null},{"id":"2603.10397","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":"2608.04382","title":"Non-asymptotic implicit bias of logistic regression at early-stage gradient descent dynamics","created":"2026-08-05","cited_by_count":0,"area":null},{"id":"2609.09595","title":"Teacher Geometry Shapes Learnability in Teacher-Student Networks","created":"2026-09-09","cited_by_count":0,"area":"distill"},{"id":"2609.34667","title":"Two-Timescale Fine-tuning Provably Learns New Features for Two-Layer ReLU Networks","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.34756","title":"Statistical Benefits of Fine-Tuning from Pretrained Initialization in Diagonal Linear Networks","created":"2026-09-28","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":"2610.16868","title":"From Parallel to Sequential: Small-Batch Noise Restores Simplicity Bias of Muon","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}