{"total":320,"rows":[{"id":"2202.07800","title":"Not All Patches are What You Need: Expediting Vision Transformers via Token Reorganizations","created":"2022-02-16","cited_by_count":363,"area":null},{"id":"2111.09839","title":"Training Neural Networks with Fixed Sparse Masks","created":"2021-11-18","cited_by_count":214,"area":null},{"id":"2106.15590","title":"The Values Encoded in Machine Learning Research","created":"2021-06-29","cited_by_count":172,"area":null},{"id":"2206.15144","title":"Neural Networks can Learn Representations with Gradient Descent","created":"2022-06-30","cited_by_count":161,"area":null},{"id":"2205.01445","title":"High-dimensional Asymptotics of Feature Learning: How One Gradient Step Improves the Representation","created":"2022-05-03","cited_by_count":150,"area":null},{"id":"2210.05643","title":"A Kernel-Based View of Language Model Fine-Tuning","created":"2022-10-11","cited_by_count":121,"area":null},{"id":"2105.15134","title":"Toward Understanding the Feature Learning Process of Self-supervised Contrastive Learning","created":"2021-05-31","cited_by_count":119,"area":null},{"id":"2101.10588","title":"Generalization error of random features and kernel methods: hypercontractivity and kernel matrix concentration","created":"2021-01-26","cited_by_count":110,"area":null},{"id":"2110.06914","title":"What Happens after SGD Reaches Zero Loss? --A Mathematical Framework","created":"2021-10-13","cited_by_count":107,"area":null},{"id":"2305.16380","title":"Scan and Snap: Understanding Training Dynamics and Token Composition in 1-layer Transformer","created":"2023-05-25","cited_by_count":102,"area":null},{"id":"2205.06643","title":"The Design Space of E(3)-Equivariant Atom-Centered Interatomic Potentials","created":"2022-05-13","cited_by_count":101,"area":null},{"id":"2109.11676","title":"Theory of overparametrization in quantum neural networks","created":"2021-09-23","cited_by_count":100,"area":null},{"id":"2206.04041","title":"Neural Collapse: A Review on Modelling Principles and Generalization","created":"2022-06-08","cited_by_count":95,"area":null},{"id":"2202.06526","title":"Benign Overfitting in Two-layer Convolutional Neural Networks","created":"2022-02-14","cited_by_count":91,"area":null},{"id":"2102.13219","title":"Learning with invariances in random features and kernel models","created":"2021-02-25","cited_by_count":89,"area":null},{"id":"2206.07085","title":"Understanding the Generalization Benefit of Normalization Layers: Sharpness Reduction","created":"2022-06-14","cited_by_count":86,"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":"2302.06015","title":"A Theoretical Understanding of Shallow Vision Transformers: Learning, Generalization, and Sample Complexity","created":"2023-02-12","cited_by_count":77,"area":null},{"id":"2112.00029","title":"Pixelated Butterfly: Simple and Efficient Sparse training for Neural Network Models","created":"2021-11-30","cited_by_count":76,"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":"2102.12470","title":"On the Validity of Modeling SGD with Stochastic Differential Equations (SDEs)","created":"2021-02-24","cited_by_count":73,"area":null},{"id":"2301.09604","title":"FedExP: Speeding Up Federated Averaging via Extrapolation","created":"2023-01-23","cited_by_count":69,"area":null},{"id":"2103.05127","title":"Model Complexity of Deep Learning: A Survey","created":"2021-03-08","cited_by_count":65,"area":null},{"id":"2410.08292","title":"Can Looped Transformers Learn to Implement Multi-step Gradient Descent for In-context Learning?","created":"2024-10-10","cited_by_count":65,"area":null},{"id":"2110.11526","title":"Wide Neural Networks Forget Less Catastrophically","created":"2021-10-21","cited_by_count":64,"area":null},{"id":"2103.03014","title":"Lost in Pruning: The Effects of Pruning Neural Networks beyond Test Accuracy","created":"2021-03-04","cited_by_count":62,"area":null},{"id":"2210.09974","title":"Theoretical Guarantees for Permutation-Equivariant Quantum Neural Networks","created":"2022-10-18","cited_by_count":52,"area":null},{"id":"2202.05834","title":"Predicting Out-of-Distribution Error with the Projection Norm","created":"2022-02-11","cited_by_count":50,"area":null},{"id":"2108.11371","title":"Understanding the Generalization of Adam in Learning Neural Networks with Proper Regularization","created":"2021-08-25","cited_by_count":49,"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":"2203.08008","title":"Beyond Explaining: Opportunities and Challenges of XAI-Based Model Improvement","created":"2022-03-15","cited_by_count":48,"area":null},{"id":"2106.03795","title":"Heavy Tails in SGD and Compressibility of Overparametrized Neural Networks","created":"2021-06-07","cited_by_count":44,"area":null},{"id":"2212.09034","title":"Graph Neural Networks are Inherently Good Generalizers: Insights by Bridging GNNs and MLPs","created":"2022-12-18","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":"2103.01210","title":"Quantifying the Benefit of Using Differentiable Learning over Tangent Kernels","created":"2021-03-01","cited_by_count":41,"area":null},{"id":"2103.06460","title":"Recent Advances on Neural Network Pruning at Initialization","created":"2021-03-11","cited_by_count":41,"area":null},{"id":"2307.11353","title":"What can a Single Attention Layer Learn? A Study Through the Random Features Lens","created":"2023-07-21","cited_by_count":40,"area":null},{"id":"2207.04036","title":"Implicit Bias of Gradient Descent on Reparametrized Models: On Equivalence to Mirror Descent","created":"2022-07-08","cited_by_count":39,"area":null},{"id":"2302.01107","title":"A Survey on Efficient Training of Transformers","created":"2023-02-02","cited_by_count":39,"area":null},{"id":"2205.06226","title":"The Mechanism of Prediction Head in Non-contrastive Self-supervised Learning","created":"2022-05-12","cited_by_count":38,"area":null},{"id":"2206.07766","title":"Pareto Invariant Risk Minimization: Towards Mitigating the Optimization Dilemma in Out-of-Distribution Generalization","created":"2022-06-15","cited_by_count":38,"area":null},{"id":"2211.16327","title":"On the Power of Foundation Models","created":"2022-11-29","cited_by_count":37,"area":null},{"id":"2306.13575","title":"Scaling MLPs: A Tale of Inductive Bias","created":"2023-06-23","cited_by_count":37,"area":null},{"id":"2303.15438","title":"On the Stepwise Nature of Self-Supervised Learning","created":"2023-03-27","cited_by_count":36,"area":null},{"id":"2102.07346","title":"On the Theory of Implicit Deep Learning: Global Convergence with Implicit Layers","created":"2021-02-15","cited_by_count":35,"area":null},{"id":"2201.12680","title":"Understanding Deep Contrastive Learning via Coordinate-wise Optimization","created":"2022-01-29","cited_by_count":35,"area":null},{"id":"2206.10012","title":"Limitations of the NTK for Understanding Generalization in Deep Learning","created":"2022-06-20","cited_by_count":35,"area":null},{"id":"2306.13253","title":"Predicting Grokking Long Before it Happens: A look into the loss landscape of models which grok","created":"2023-06-23","cited_by_count":35,"area":null},{"id":"2402.15607","title":"How Do Nonlinear Transformers Learn and Generalize in In-Context Learning?","created":"2024-02-23","cited_by_count":35,"area":null},{"id":"2106.05932","title":"Early-stopped neural networks are consistent","created":"2021-06-10","cited_by_count":34,"area":null},{"id":"2106.04013","title":"The Future is Log-Gaussian: ResNets and Their Infinite-Depth-and-Width Limit at Initialization","created":"2021-06-07","cited_by_count":33,"area":null},{"id":"2111.13293","title":"KNAS: Green Neural Architecture Search","created":"2021-11-26","cited_by_count":33,"area":null},{"id":"2505.10833","title":"MergeBench: A Benchmark for Merging Domain-Specialized LLMs","created":"2025-05-16","cited_by_count":33,"area":null},{"id":"2201.07705","title":"GEMEL: Model Merging for Memory-Efficient, Real-Time Video Analytics at the Edge","created":"2022-01-19","cited_by_count":32,"area":null},{"id":"2210.04345","title":"LieGG: Studying Learned Lie Group Generators","created":"2022-10-09","cited_by_count":31,"area":null},{"id":"2211.06506","title":"Spectral Evolution and Invariance in Linear-width Neural Networks","created":"2022-11-11","cited_by_count":30,"area":null},{"id":"2301.13139","title":"A Novel Framework for Policy Mirror Descent with General Parameterization and Linear Convergence","created":"2023-01-30","cited_by_count":30,"area":null},{"id":"2108.07686","title":"Scaling Laws for Deep Learning","created":"2021-08-17","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":"2203.10036","title":"On the Generalization Mystery in Deep Learning","created":"2022-03-18","cited_by_count":25,"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":"2203.16462","title":"Convergence of gradient descent for deep neural networks","created":"2022-03-30","cited_by_count":24,"area":null},{"id":"2207.03584","title":"Generalization Guarantee of Training Graph Convolutional Networks with Graph Topology Sampling","created":"2022-07-07","cited_by_count":23,"area":null},{"id":"2209.13570","title":"Hierarchical Sliced Wasserstein Distance","created":"2022-09-27","cited_by_count":23,"area":null},{"id":"2107.05074","title":"SGD: The Role of Implicit Regularization, Batch-size and Multiple-epochs","created":"2021-07-11","cited_by_count":22,"area":null},{"id":"2208.04508","title":"Training Overparametrized Neural Networks in Sublinear Time","created":"2022-08-09","cited_by_count":22,"area":null},{"id":"2208.05395","title":"A Sublinear Adversarial Training Algorithm","created":"2022-08-10","cited_by_count":22,"area":null},{"id":"2106.06529","title":"The Limitations of Large Width in Neural Networks: A Deep Gaussian Process Perspective","created":"2021-06-11","cited_by_count":21,"area":null},{"id":"2106.13792","title":"Proxy Convexity: A Unified Framework for the Analysis of Neural Networks Trained by Gradient Descent","created":"2021-06-25","cited_by_count":21,"area":null},{"id":"2209.09298","title":"Stability and Generalization Analysis of Gradient Methods for Shallow Neural Networks","created":"2022-09-19","cited_by_count":21,"area":null},{"id":"2212.14457","title":"Bayesian Interpolation with Deep Linear Networks","created":"2022-12-29","cited_by_count":21,"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":"2307.01998","title":"Zero-Shot Neural Architecture Search: Challenges, Solutions, and Opportunities","created":"2023-07-05","cited_by_count":21,"area":null},{"id":"2402.01929","title":"Sample, estimate, aggregate: A recipe for causal discovery foundation models","created":"2024-02-02","cited_by_count":21,"area":null},{"id":"2402.04084","title":"Provably learning a multi-head attention layer","created":"2024-02-06","cited_by_count":21,"area":null},{"id":"2105.00303","title":"RATT: Leveraging Unlabeled Data to Guarantee Generalization","created":"2021-05-01","cited_by_count":20,"area":null},{"id":"2106.04975","title":"The dilemma of quantum neural networks","created":"2021-06-09","cited_by_count":20,"area":null},{"id":"2106.06573","title":"Understanding Deflation Process in Over-parametrized Tensor Decomposition","created":"2021-06-11","cited_by_count":20,"area":null},{"id":"2106.10744","title":"On the Cryptographic Hardness of Learning Single Periodic Neurons","created":"2021-06-20","cited_by_count":20,"area":null},{"id":"2110.09771","title":"On Reward-Free RL with Kernel and Neural Function Approximations: Single-Agent MDP and Markov Game","created":"2021-10-19","cited_by_count":20,"area":null},{"id":"2301.01597","title":"Problem-Dependent Power of Quantum Neural Networks on Multi-Class Classification","created":"2022-12-29","cited_by_count":20,"area":null},{"id":"2306.00788","title":"Understanding Augmentation-based Self-Supervised Representation Learning via RKHS Approximation and Regression","created":"2023-06-01","cited_by_count":20,"area":null},{"id":"2401.07187","title":"A Survey on Statistical Theory of Deep Learning: Approximation, Training Dynamics, and Generative Models","created":"2024-01-14","cited_by_count":20,"area":null},{"id":"2104.05508","title":"Noether: The More Things Change, the More Stay the Same","created":"2021-04-12","cited_by_count":19,"area":null},{"id":"2201.08514","title":"How does unlabeled data improve generalization in self-training? A one-hidden-layer theoretical analysis","created":"2022-01-21","cited_by_count":19,"area":null},{"id":"2305.06986","title":"Provable Guarantees for Nonlinear Feature Learning in Three-Layer Neural Networks","created":"2023-05-11","cited_by_count":19,"area":null},{"id":"2202.09318","title":"DataMUX: Data Multiplexing for Neural Networks","created":"2022-02-18","cited_by_count":18,"area":null},{"id":"2310.01769","title":"How Over-Parameterization Slows Down Gradient Descent in Matrix Sensing: The Curses of Symmetry and Initialization","created":"2023-10-03","cited_by_count":18,"area":null},{"id":"2112.02393","title":"Optimization-Based Separations for Neural Networks","created":"2021-12-04","cited_by_count":17,"area":null},{"id":"2208.03635","title":"Federated Adversarial Learning: A Framework with Convergence Analysis","created":"2022-08-07","cited_by_count":17,"area":null},{"id":"2507.12224","title":"Optimizers Qualitatively Alter Solutions And We Should Leverage This","created":"2025-07-16","cited_by_count":17,"area":null},{"id":"2103.02695","title":"Shift Invariance Can Reduce Adversarial Robustness","created":"2021-03-03","cited_by_count":16,"area":null},{"id":"2212.14852","title":"An Analysis of Attention via the Lens of Exchangeability and Latent Variable Models","created":"2022-12-30","cited_by_count":16,"area":null},{"id":"2302.02922","title":"Joint Edge-Model Sparse Learning is Provably Efficient for Graph Neural Networks","created":"2023-02-06","cited_by_count":16,"area":null},{"id":"2306.00242","title":"Combinatorial Neural Bandits","created":"2023-05-31","cited_by_count":16,"area":null},{"id":"2307.06887","title":"Provable Multi-Task Representation Learning by Two-Layer ReLU Neural Networks","created":"2023-07-13","cited_by_count":16,"area":null},{"id":"2108.11018","title":"A Scaling Law for Synthetic-to-Real Transfer: How Much Is Your Pre-training Effective?","created":"2021-08-25","cited_by_count":15,"area":null},{"id":"2206.12802","title":"Bounding the Width of Neural Networks via Coupled Initialization -- A Worst Case Analysis","created":"2022-06-26","cited_by_count":15,"area":null},{"id":"2403.12329","title":"FedFisher: Leveraging Fisher Information for One-Shot Federated Learning","created":"2024-03-19","cited_by_count":15,"area":null},{"id":"2102.07567","title":"Learning Accurate Decision Trees with Bandit Feedback via Quantized Gradient Descent","created":"2021-02-15","cited_by_count":14,"area":null}],"next_cursor":"100"}