{"list":"other","total":97,"rows":[{"id":"1806.07572","title":"Neural Tangent Kernel: Convergence and Generalization in Neural Networks","created":"2018-06-20","cited_by_count":2621},{"id":"1803.03635","title":"The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks","created":"2018-03-09","cited_by_count":2262},{"id":"1811.12231","title":"ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness","created":"2018-11-29","cited_by_count":1432},{"id":"1806.08734","title":"On the Spectral Bias of Neural Networks","created":"2018-06-22","cited_by_count":1341},{"id":"2209.10652","title":"Toy Models of Superposition","created":"2022-09-21","cited_by_count":971},{"id":"1706.05394","title":"A Closer Look at Memorization in Deep Networks","created":"2017-06-16","cited_by_count":942},{"id":"1312.6120","title":"Exact solutions to the nonlinear dynamics of learning in deep linear neural networks","created":"2013-12-20","cited_by_count":763},{"id":"2208.01066","title":"What Can Transformers Learn In-Context? A Case Study of Simple Function Classes","created":"2022-08-01","cited_by_count":715},{"id":"1812.07956","title":"On Lazy Training in Differentiable Programming","created":"2018-12-19","cited_by_count":675},{"id":"2006.07710","title":"The Pitfalls of Simplicity Bias in Neural Networks","created":"2020-06-13","cited_by_count":351},{"id":"1710.03667","title":"High-dimensional dynamics of generalization error in neural networks","created":"2017-10-10","cited_by_count":241},{"id":"1605.07110","title":"Deep Learning without Poor Local Minima","created":"2016-05-23","cited_by_count":234},{"id":"2403.17887","title":"The Unreasonable Ineffectiveness of the Deeper Layers","created":"2024-03-26","cited_by_count":226},{"id":"1905.11604","title":"SGD on Neural Networks Learns Functions of Increasing Complexity","created":"2019-05-28","cited_by_count":204},{"id":"1810.10531","title":"A mathematical theory of semantic development in deep neural networks","created":"2018-10-23","cited_by_count":186},{"id":"1805.08522","title":"Deep learning generalizes because the parameter-function map is biased towards simple functions","created":"2018-05-22","cited_by_count":183},{"id":"1810.02032","title":"Gradient descent aligns the layers of deep linear networks","created":"2018-10-04","cited_by_count":182},{"id":"2006.06657","title":"Directional convergence and alignment in deep learning","created":"2020-06-11","cited_by_count":178},{"id":"1912.01198","title":"Towards Understanding the Spectral Bias of Deep Learning","created":"2019-12-03","cited_by_count":174},{"id":"2103.10427","title":"The Low-Rank Simplicity Bias in Deep Networks","created":"2021-03-18","cited_by_count":154},{"id":"2012.09839","title":"Towards Resolving the Implicit Bias of Gradient Descent for Matrix Factorization: Greedy Low-Rank Learning","created":"2020-12-17","cited_by_count":150},{"id":"2302.11055","title":"SGD learning on neural networks: leap complexity and saddle-to-saddle dynamics","created":"2023-02-21","cited_by_count":143},{"id":"2105.12221","title":"Geometry of the Loss Landscape in Overparameterized Neural Networks: Symmetries and Invariances","created":"2021-05-25","cited_by_count":127},{"id":"2006.12433","title":"What shapes feature representations? Exploring datasets, architectures, and training","created":"2020-06-22","cited_by_count":126},{"id":"1904.13262","title":"Implicit Regularization of Discrete Gradient Dynamics in Linear Neural Networks","created":"2019-04-30","cited_by_count":124},{"id":"2402.11004","title":"The Evolution of Statistical Induction Heads: In-Context Learning Markov Chains","created":"2024-02-16","cited_by_count":118},{"id":"2111.00034","title":"Neural Networks as Kernel Learners: The Silent Alignment Effect","created":"2021-10-29","cited_by_count":106},{"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},{"id":"2105.05612","title":"Evading the Simplicity Bias: Training a Diverse Set of Models Discovers Solutions with Superior OOD Generalization","created":"2021-05-12","cited_by_count":83},{"id":"2110.13905","title":"Gradient Descent on Two-layer Nets: Margin Maximization and Simplicity Bias","created":"2021-10-26","cited_by_count":83},{"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},{"id":"2211.12316","title":"Simplicity Bias in Transformers and their Ability to Learn Sparse Boolean Functions","created":"2022-11-22","cited_by_count":70},{"id":"2007.07497","title":"Phase diagram for two-layer ReLU neural networks at infinite-width limit","created":"2020-07-15","cited_by_count":67},{"id":"1712.01473","title":"Deep linear neural networks with arbitrary loss: All local minima are global","created":"2017-12-05","cited_by_count":65},{"id":"1909.12051","title":"The Implicit Bias of Depth: How Incremental Learning Drives Generalization","created":"2019-09-26","cited_by_count":64},{"id":"2304.05366","title":"The No Free Lunch Theorem, Kolmogorov Complexity, and the Role of Inductive Biases in Machine Learning","created":"2023-04-11","cited_by_count":63},{"id":"1803.08367","title":"Gradient Descent Quantizes ReLU Network Features","created":"2018-03-22","cited_by_count":61},{"id":"2006.14599","title":"The Surprising Simplicity of the Early-Time Learning Dynamics of Neural Networks","created":"2020-06-25","cited_by_count":58},{"id":"2303.00055","title":"Learning time-scales in two-layers neural networks","created":"2023-02-28","cited_by_count":57},{"id":"2304.00488","title":"Saddle-to-Saddle Dynamics in Diagonal Linear Networks","created":"2023-04-02","cited_by_count":57},{"id":"2201.12760","title":"Implicit Regularization Towards Rank Minimization in ReLU Networks","created":"2022-01-30","cited_by_count":53},{"id":"2306.07042","title":"Transformers learn through gradual rank increase","created":"2023-06-12","cited_by_count":52},{"id":"2006.15191","title":"Is SGD a Bayesian sampler? Well, almost","created":"2020-06-26","cited_by_count":50},{"id":"2211.11567","title":"Neural networks trained with SGD learn distributions of increasing complexity","created":"2022-11-21","cited_by_count":50},{"id":"2409.14623","title":"From Lazy to Rich: Exact Learning Dynamics in Deep Linear Networks","created":"2024-09-22","cited_by_count":49},{"id":"2210.07082","title":"Implicit Bias in Leaky ReLU Networks Trained on High-Dimensional Data","created":"2022-10-13","cited_by_count":46},{"id":"2410.06833","title":"Dynamic metastability in the self-attention model","created":"2024-10-09","cited_by_count":46},{"id":"2501.16265","title":"Training Dynamics of In-Context Learning in Linear Attention","created":"2025-01-27","cited_by_count":46},{"id":"2305.18761","title":"Identifying Spurious Biases Early in Training through the Lens of Simplicity Bias","created":"2023-05-30","cited_by_count":44},{"id":"2403.02241","title":"Neural Redshift: Random Networks are not Random Functions","created":"2024-03-04","cited_by_count":43},{"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},{"id":"1904.11455","title":"Ray Interference: a Source of Plateaus in Deep Reinforcement Learning","created":"2019-04-25","cited_by_count":40},{"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},{"id":"2105.14573","title":"Embedding Principle of Loss Landscape of Deep Neural Networks","created":"2021-05-30","cited_by_count":38},{"id":"2303.15438","title":"On the Stepwise Nature of Self-Supervised Learning","created":"2023-03-27","cited_by_count":36},{"id":"2202.07626","title":"Random Feature Amplification: Feature Learning and Generalization in Neural Networks","created":"2022-02-15","cited_by_count":35},{"id":"2210.17216","title":"Symmetries, flat minima, and the conserved quantities of gradient flow","created":"2022-10-31","cited_by_count":35},{"id":"2201.11968","title":"Training invariances and the low-rank phenomenon: beyond linear networks","created":"2022-01-28","cited_by_count":33},{"id":"1707.02444","title":"Global optimality conditions for deep neural networks","created":"2017-07-08","cited_by_count":31},{"id":"1906.04868","title":"Semi-flat minima and saddle points by embedding neural networks to overparameterization","created":"2019-06-12","cited_by_count":30},{"id":"1702.08580","title":"Depth Creates No Bad Local Minima","created":"2017-02-27","cited_by_count":29},{"id":"2208.14673","title":"Incremental Learning in Diagonal Linear Networks","created":"2022-08-31","cited_by_count":28},{"id":"2304.06670","title":"Deep neural networks have an inbuilt Occam's razor","created":"2023-04-13","cited_by_count":28},{"id":"2307.12851","title":"Early Neuron Alignment in Two-layer ReLU Networks with Small Initialization","created":"2023-07-24","cited_by_count":28},{"id":"2503.03206","title":"An Analytical Theory of Spectral Bias in the Learning Dynamics of Diffusion Models","created":"2025-03-05","cited_by_count":26},{"id":"2107.13289","title":"The loss landscape of deep linear neural networks: a second-order analysis","created":"2021-07-28","cited_by_count":24},{"id":"2410.19637","title":"A distributional simplicity bias in the learning dynamics of transformers","created":"2024-10-25","cited_by_count":24},{"id":"2001.03371","title":"Data-Dependence of Plateau Phenomenon in Learning with Neural Network --- Statistical Mechanical Analysis","created":"2020-01-10","cited_by_count":23},{"id":"2206.12314","title":"Learning sparse features can lead to overfitting in neural networks","created":"2022-06-24","cited_by_count":23},{"id":"1809.08587","title":"Exponential Convergence Time of Gradient Descent for One-Dimensional Deep Linear Neural Networks","created":"2018-09-23","cited_by_count":22},{"id":"2111.07167","title":"The Three Stages of Learning Dynamics in High-Dimensional Kernel Methods","created":"2021-11-13","cited_by_count":22},{"id":"2101.02533","title":"Towards Understanding Learning in Neural Networks with Linear Teachers","created":"2021-01-07","cited_by_count":19},{"id":"2304.09576","title":"Leveraging the two timescale regime to demonstrate convergence of neural networks","created":"2023-04-19","cited_by_count":19},{"id":"2312.00935","title":"Understanding Unimodal Bias in Multimodal Deep Linear Networks","created":"2023-12-01","cited_by_count":19},{"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},{"id":"2401.10791","title":"Early alignment in two-layer networks training is a two-edged sword","created":"2024-01-19","cited_by_count":18},{"id":"2405.17580","title":"Mixed Dynamics In Linear Networks: Unifying the Lazy and Active Regimes","created":"2024-05-27","cited_by_count":18},{"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},{"id":"2506.17859","title":"In-Context Learning Strategies Emerge Rationally","created":"2025-06-21","cited_by_count":16},{"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},{"id":"2305.12467","title":"Understanding Multi-phase Optimization Dynamics and Rich Nonlinear Behaviors of ReLU Networks","created":"2023-05-21","cited_by_count":15},{"id":"2310.08513","title":"How connectivity structure shapes rich and lazy learning in neural circuits","created":"2023-10-12","cited_by_count":15},{"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},{"id":"2502.05300","title":"Parameter Symmetry Potentially Unifies Deep Learning Theory","created":"2025-02-07","cited_by_count":12},{"id":"2402.09226","title":"Directional Convergence Near Small Initializations and Saddles in Two-Homogeneous Neural Networks","created":"2024-02-14","cited_by_count":11},{"id":"2405.17299","title":"Simplicity Bias of Two-Layer Networks beyond Linearly Separable Data","created":"2024-05-27","cited_by_count":11},{"id":"2410.02348","title":"Simplicity bias and optimization threshold in two-layer ReLU networks","created":"2024-10-03","cited_by_count":11},{"id":"2408.11979","title":"Only Strict Saddles in the Energy Landscape of Predictive Coding Networks?","created":"2024-08-21","cited_by_count":10},{"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},{"id":"2002.04861","title":"Training Two-Layer ReLU Networks with Gradient Descent is Inconsistent","created":"2020-02-12","cited_by_count":6},{"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},{"id":"2406.06504","title":"Equivariant Neural Tangent Kernels","created":"2024-06-10","cited_by_count":4},{"id":"2406.12615","title":"When Are Bias-Free ReLU Networks Effectively Linear Networks?","created":"2024-06-18","cited_by_count":4},{"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},{"id":"2509.18766","title":"Diagonal Linear Networks and the Lasso Regularization Path","created":"2025-09-23","cited_by_count":4},{"id":"2406.17467","title":"Early learning of the optimal constant solution in neural networks and humans","created":"2024-06-25","cited_by_count":3},{"id":"2505.13567","title":"Learning Dynamics of RNNs in Closed-Loop Environments","created":"2025-05-19","cited_by_count":2}],"next_cursor":null}