{"total":120,"rows":[{"id":"2202.10054","title":"Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution","created":"2022-02-21","cited_by_count":739,"area":null},{"id":"2105.02375","title":"A Geometric Analysis of Neural Collapse with Unconstrained Features","created":"2021-05-06","cited_by_count":227,"area":null},{"id":"2103.10427","title":"The Low-Rank Simplicity Bias in Deep Networks","created":"2021-03-18","cited_by_count":154,"area":null},{"id":"2110.02796","title":"An Unconstrained Layer-Peeled Perspective on Neural Collapse","created":"2021-10-06","cited_by_count":87,"area":null},{"id":"2106.15933","title":"Saddle-to-Saddle Dynamics in Deep Linear Networks: Small Initialization Training, Symmetry, and Sparsity","created":"2021-06-30","cited_by_count":85,"area":null},{"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":"2209.14863","title":"Neural Networks Efficiently Learn Low-Dimensional Representations with SGD","created":"2022-09-29","cited_by_count":63,"area":null},{"id":"2108.10573","title":"The staircase property: How hierarchical structure can guide deep learning","created":"2021-08-24","cited_by_count":62,"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":"2201.12760","title":"Implicit Regularization Towards Rank Minimization in ReLU Networks","created":"2022-01-30","cited_by_count":53,"area":null},{"id":"2306.07042","title":"Transformers learn through gradual rank increase","created":"2023-06-12","cited_by_count":52,"area":null},{"id":"2409.14623","title":"From Lazy to Rich: Exact Learning Dynamics in Deep Linear Networks","created":"2024-09-22","cited_by_count":49,"area":null},{"id":"2102.09972","title":"Implicit Regularization in Tensor Factorization","created":"2021-02-19","cited_by_count":44,"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":"2110.02732","title":"On Margin Maximization in Linear and ReLU Networks","created":"2021-10-06","cited_by_count":34,"area":null},{"id":"2108.05574","title":"Implicit Sparse Regularization: The Impact of Depth and Early Stopping","created":"2021-08-12","cited_by_count":30,"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":"2604.21691","title":"There Will Be a Scientific Theory of Deep Learning","created":"2026-04-23","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":"2201.02115","title":"The dynamics of representation learning in shallow, non-linear autoencoders","created":"2022-01-06","cited_by_count":27,"area":null},{"id":"2201.11729","title":"Implicit Regularization in Hierarchical Tensor Factorization and Deep Convolutional Neural Networks","created":"2022-01-27","cited_by_count":27,"area":null},{"id":"2206.04613","title":"Explicit Regularization in Overparametrized Models via Noise Injection","created":"2022-06-09","cited_by_count":26,"area":null},{"id":"2406.04112","title":"Compressible Dynamics in Deep Overparameterized Low-Rank Learning & Adaptation","created":"2024-06-06","cited_by_count":26,"area":null},{"id":"2107.13289","title":"The loss landscape of deep linear neural networks: a second-order analysis","created":"2021-07-28","cited_by_count":24,"area":null},{"id":"2112.11027","title":"More is Less: Inducing Sparsity via Overparameterization","created":"2021-12-21","cited_by_count":24,"area":null},{"id":"2210.11075","title":"Freeze then Train: Towards Provable Representation Learning under Spurious Correlations and Feature Noise","created":"2022-10-20","cited_by_count":22,"area":null},{"id":"2202.08788","title":"Global Convergence of Sub-gradient Method for Robust Matrix Recovery: Small Initialization, Noisy Measurements, and Over-parameterization","created":"2022-02-17","cited_by_count":21,"area":null},{"id":"2211.16980","title":"Infinite-width limit of deep linear neural networks","created":"2022-11-29","cited_by_count":20,"area":null},{"id":"2306.01154","title":"The Law of Parsimony in Gradient Descent for Learning Deep Linear Networks","created":"2023-06-01","cited_by_count":20,"area":null},{"id":"2305.11041","title":"High-dimensional Asymptotics of Denoising Autoencoders","created":"2023-05-18","cited_by_count":19,"area":null},{"id":"2312.00935","title":"Understanding Unimodal Bias in Multimodal Deep Linear Networks","created":"2023-12-01","cited_by_count":19,"area":null},{"id":"2403.08699","title":"Implicit Regularization of Gradient Flow on One-Layer Softmax Attention","created":"2024-03-13","cited_by_count":19,"area":null},{"id":"2510.22980","title":"How Muon's Spectral Design Benefits Generalization: A Study on Imbalanced Data","created":"2025-10-27","cited_by_count":19,"area":null},{"id":"2405.17580","title":"Mixed Dynamics In Linear Networks: Unifying the Lazy and Active Regimes","created":"2024-05-27","cited_by_count":18,"area":null},{"id":"2405.13456","title":"Deep linear networks for regression are implicitly regularized towards flat minima","created":"2024-05-22","cited_by_count":17,"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":"2306.17499","title":"The Implicit Bias of Minima Stability in Multivariate Shallow ReLU Networks","created":"2023-06-30","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":"2102.08373","title":"Analysis of feature learning in weight-tied autoencoders via the mean field lens","created":"2021-02-16","cited_by_count":14,"area":null},{"id":"2411.01248","title":"Guiding Neural Collapse: Optimising Towards the Nearest Simplex Equiangular Tight Frame","created":"2024-11-02","cited_by_count":14,"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":"2305.05448","title":"Robust Implicit Regularization via Weight Normalization","created":"2023-05-09","cited_by_count":12,"area":null},{"id":"2307.07785","title":"The Interpolating Information Criterion for Overparameterized Models","created":"2023-07-15","cited_by_count":12,"area":null},{"id":"2206.11872","title":"Provable Acceleration of Heavy Ball beyond Quadratics for a Class of Polyak-\\L{}ojasiewicz Functions when the Non-Convexity is Averaged-Out","created":"2022-06-22","cited_by_count":11,"area":null},{"id":"2105.05553","title":"Principal Components Bias in Over-parameterized Linear Models, and its Manifestation in Deep Neural Networks","created":"2021-05-12","cited_by_count":10,"area":null},{"id":"2410.14802","title":"Implicit Regularization of Sharpness-Aware Minimization for Scale-Invariant Problems","created":"2024-10-18","cited_by_count":10,"area":null},{"id":"2602.03655","title":"Sequential Group Composition: A Window into the Mechanics of Deep Learning","created":"2026-02-03","cited_by_count":10,"area":null},{"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":"2502.21009","title":"Position: Solve Layerwise Linear Models First to Understand Neural Dynamical Phenomena (Neural Collapse, Emergence, Lazy/Rich Regime, and Grokking)","created":"2025-02-28","cited_by_count":9,"area":null},{"id":"2406.11110","title":"How Neural Networks Learn the Support is an Implicit Regularization Effect of SGD","created":"2024-06-17","cited_by_count":8,"area":null},{"id":"2502.09863","title":"Closed-Form Training Dynamics Reveal Learned Features and Linear Structure in Word2Vec-like Models","created":"2025-02-14","cited_by_count":8,"area":null},{"id":"2303.02034","title":"Linear CNNs Discover the Statistical Structure of the Dataset Using Only the Most Dominant Frequencies","created":"2023-03-03","cited_by_count":7,"area":null},{"id":"2303.03027","title":"Critical Points and Convergence Analysis of Generative Deep Linear Networks Trained with Bures-Wasserstein Loss","created":"2023-03-06","cited_by_count":7,"area":null},{"id":"2402.12118","title":"Sparse, Efficient and Explainable Data Attribution with DualXDA","created":"2024-02-19","cited_by_count":6,"area":null},{"id":"2105.06351","title":"Convergence and Implicit Bias of Gradient Flow on Overparametrized Linear Networks","created":"2021-05-13","cited_by_count":5,"area":null},{"id":"2106.15456","title":"A Mechanism for Producing Aligned Latent Spaces with Autoencoders","created":"2021-06-29","cited_by_count":5,"area":null},{"id":"2202.00790","title":"On Regularizing Coordinate-MLPs","created":"2022-02-01","cited_by_count":5,"area":null},{"id":"2206.08558","title":"How You Start Matters for Generalization","created":"2022-06-17","cited_by_count":5,"area":null},{"id":"2209.09658","title":"Lazy vs hasty: linearization in deep networks impacts learning schedule based on example difficulty","created":"2022-09-19","cited_by_count":5,"area":null},{"id":"2307.01177","title":"Neural Hilbert Ladders: Multi-Layer Neural Networks in Function Space","created":"2023-07-03","cited_by_count":5,"area":null},{"id":"2402.05013","title":"Compression of Structured Data with Autoencoders: Provable Benefit of Nonlinearities and Depth","created":"2024-02-07","cited_by_count":5,"area":null},{"id":"2402.13891","title":"Overcoming Saturation in Density Ratio Estimation by Iterated Regularization","created":"2024-02-21","cited_by_count":5,"area":null},{"id":"2205.10697","title":"Lassoed Tree Boosting","created":"2022-05-22","cited_by_count":4,"area":null},{"id":"2209.10634","title":"Interneurons accelerate learning dynamics in recurrent neural networks for statistical adaptation","created":"2022-09-21","cited_by_count":4,"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":"2409.05800","title":"Input Space Mode Connectivity in Deep Neural Networks","created":"2024-09-09","cited_by_count":4,"area":null},{"id":"2505.11664","title":"A Local Polyak-Lojasiewicz and Descent Lemma of Gradient Descent For Overparametrized Linear Models","created":"2025-05-16","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":"2602.16167","title":"Muon with Spectral Guidance: Efficient Optimization for Scientific Machine Learning","created":"2026-02-18","cited_by_count":4,"area":null},{"id":"2605.12705","title":"Early Data Exposure Improves Robustness to Subsequent Fine-Tuning","created":"2026-05-12","cited_by_count":4,"area":null},{"id":"2102.08581","title":"Efficient Scheduling of Data Augmentation for Deep Reinforcement Learning","created":"2021-02-17","cited_by_count":3,"area":null},{"id":"2206.00823","title":"Beyond accuracy: generalization properties of bio-plausible temporal credit assignment rules","created":"2022-06-02","cited_by_count":3,"area":null},{"id":"2212.13468","title":"Fundamental Limits of Two-layer Autoencoders, and Achieving Them with Gradient Methods","created":"2022-12-27","cited_by_count":3,"area":null},{"id":"2307.10317","title":"FedBug: A Bottom-Up Gradual Unfreezing Framework for Federated Learning","created":"2023-07-19","cited_by_count":3,"area":null},{"id":"2311.05061","title":"Efficient Compression of Overparameterized Deep Models through Low-Dimensional Learning Dynamics","created":"2023-11-08","cited_by_count":3,"area":null},{"id":"2405.13721","title":"Connectivity Shapes Implicit Regularization in Matrix Factorization Models for Matrix Completion","created":"2024-05-22","cited_by_count":3,"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":"2606.30509","title":"Muon learns balanced solutions in matrix factorization without slow saddle-to-saddle dynamics","created":"2026-06-29","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":"2309.16109","title":"Feature Normalization Prevents Collapse of Non-contrastive Learning Dynamics","created":"2023-09-28","cited_by_count":2,"area":null},{"id":"2410.04264","title":"Decoupling Dynamical Richness from Representation Learning: Towards Practical Measurement","created":"2024-10-05","cited_by_count":2,"area":null},{"id":"2501.09137","title":"Gradient Descent Converges Linearly to Flatter Minima than Gradient Flow in Shallow Linear Networks","created":"2025-01-15","cited_by_count":2,"area":null},{"id":"2505.08348","title":"Geometry of Semantics in Next-Token Prediction: How Optimization Implicitly Organizes Linguistic Representations","created":"2025-05-13","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":"2512.04006","title":"Diagonalizing the Softmax: Hadamard Initialization for Tractable Cross-Entropy Dynamics","created":"2025-12-03","cited_by_count":2,"area":null},{"id":"2601.06961","title":"The Impact of Anisotropic Covariance Structure on the Training Dynamics and Generalization Error of Linear Networks","created":"2026-01-11","cited_by_count":2,"area":null},{"id":"2601.12011","title":"Why Loss Re-weighting Works If You Stop Early: Training Dynamics of Unconstrained Features","created":"2026-01-17","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":"2602.19533","title":"Grokking Finite-Dimensional Algebra","created":"2026-02-23","cited_by_count":2,"area":null},{"id":"2606.23198","title":"Incremental Learning in Mirror Flows","created":"2026-06-22","cited_by_count":2,"area":null},{"id":"2110.10815","title":"Convergence Analysis and Implicit Regularization of Feedback Alignment for Deep Linear Networks","created":"2021-10-20","cited_by_count":1,"area":null},{"id":"2206.02454","title":"What do CNNs Learn in the First Layer and Why? A Linear Systems Perspective","created":"2022-06-06","cited_by_count":1,"area":null},{"id":"2206.15058","title":"A note on Linear Bottleneck networks and their Transition to Multilinearity","created":"2022-06-30","cited_by_count":1,"area":null},{"id":"2212.14150","title":"A Dynamics Theory of Implicit Regularization in Deep Low-Rank Matrix Factorization","created":"2022-12-29","cited_by_count":1,"area":null},{"id":"2310.16194","title":"Learning Low-Rank Latent Spaces with Simple Deterministic Autoencoder: Theoretical and Empirical Insights","created":"2023-10-24","cited_by_count":1,"area":null},{"id":"2311.14120","title":"Weight fluctuations in (deep) linear neural networks and a derivation of the inverse-variance flatness relation","created":"2023-11-23","cited_by_count":1,"area":null},{"id":"2402.17595","title":"Implicit Regularization via Spectral Neural Networks and Non-linear Matrix Sensing","created":"2024-02-27","cited_by_count":1,"area":null}],"next_cursor":"100"}