{"total":76,"rows":[{"id":"2402.04333","title":"LESS: Selecting Influential Data for Targeted Instruction Tuning","created":"2024-02-06","cited_by_count":532,"area":null},{"id":"2107.13034","title":"Dataset Distillation with Infinitely Wide Convolutional Networks","created":"2021-07-27","cited_by_count":218,"area":null},{"id":"2106.12627","title":"Provably efficient machine learning for quantum many-body problems","created":"2021-06-23","cited_by_count":91,"area":null},{"id":"2203.06176","title":"More Than a Toy: Random Matrix Models Predict How Real-World Neural Representations Generalize","created":"2022-03-11","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":"2102.11742","title":"Classifying high-dimensional Gaussian mixtures: Where kernel methods fail and neural networks succeed","created":"2021-02-23","cited_by_count":69,"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":"2310.11046","title":"Fast Graph Condensation with Structure-based Neural Tangent Kernel","created":"2023-10-17","cited_by_count":36,"area":null},{"id":"2103.01439","title":"Fast Adaptation with Linearized Neural Networks","created":"2021-03-02","cited_by_count":32,"area":null},{"id":"2102.10032","title":"Approximation and Learning with Deep Convolutional Models: a Kernel Perspective","created":"2021-02-19","cited_by_count":31,"area":null},{"id":"2202.12230","title":"Sample Efficiency of Data Augmentation Consistency Regularization","created":"2022-02-24","cited_by_count":28,"area":null},{"id":"2303.14269","title":"The Exact Sample Complexity Gain from Invariances for Kernel Regression","created":"2023-03-24","cited_by_count":28,"area":null},{"id":"2112.08297","title":"Rethinking Influence Functions of Neural Networks in the Over-parameterized Regime","created":"2021-12-15","cited_by_count":26,"area":null},{"id":"2206.12569","title":"Making Look-Ahead Active Learning Strategies Feasible with Neural Tangent Kernels","created":"2022-06-25","cited_by_count":25,"area":null},{"id":"2210.05021","title":"The good, the bad and the ugly sides of data augmentation: An implicit spectral regularization perspective","created":"2022-10-10","cited_by_count":24,"area":null},{"id":"2111.07167","title":"The Three Stages of Learning Dynamics in High-Dimensional Kernel Methods","created":"2021-11-13","cited_by_count":22,"area":null},{"id":"2111.08308","title":"Learning with convolution and pooling operations in kernel methods","created":"2021-11-16","cited_by_count":21,"area":null},{"id":"2308.13431","title":"Six Lectures on Linearized Neural Networks","created":"2023-08-25","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":"2206.04672","title":"Overcoming the Spectral Bias of Neural Value Approximation","created":"2022-06-09","cited_by_count":19,"area":null},{"id":"2305.18512","title":"A Rainbow in Deep Network Black Boxes","created":"2023-05-29","cited_by_count":18,"area":null},{"id":"2403.03103","title":"Emergent Equivariance in Deep Ensembles","created":"2024-03-05","cited_by_count":18,"area":null},{"id":"2309.00570","title":"Mechanism of feature learning in convolutional neural networks","created":"2023-09-01","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":"2301.10808","title":"Graph Neural Tangent Kernel: Convergence on Large Graphs","created":"2023-01-25","cited_by_count":16,"area":null},{"id":"2106.03227","title":"Neural Tangent Kernel Maximum Mean Discrepancy","created":"2021-06-06","cited_by_count":15,"area":null},{"id":"2210.05929","title":"Few-shot Backdoor Attacks via Neural Tangent Kernels","created":"2022-10-12","cited_by_count":15,"area":null},{"id":"2104.14132","title":"Generalization Guarantees for Neural Architecture Search with Train-Validation Split","created":"2021-04-29","cited_by_count":14,"area":null},{"id":"2110.07641","title":"Non-deep Networks","created":"2021-10-14","cited_by_count":14,"area":null},{"id":"2111.02951","title":"Quantum tangent kernel","created":"2021-11-04","cited_by_count":14,"area":null},{"id":"2201.04753","title":"Largest Eigenvalues of the Conjugate Kernel of Single-Layered Neural Networks","created":"2022-01-13","cited_by_count":13,"area":null},{"id":"2302.02605","title":"Toward Large Kernel Models","created":"2023-02-06","cited_by_count":13,"area":null},{"id":"2110.12122","title":"Quantifying Epistemic Uncertainty in Deep Learning","created":"2021-10-23","cited_by_count":10,"area":null},{"id":"2306.05674","title":"Efficient Uncertainty Quantification and Reduction for Over-Parameterized Neural Networks","created":"2023-06-09","cited_by_count":10,"area":null},{"id":"2303.05420","title":"Kernel Regression with Infinite-Width Neural Networks on Millions of Examples","created":"2023-03-09","cited_by_count":9,"area":null},{"id":"2307.14531","title":"Controlling the Inductive Bias of Wide Neural Networks by Modifying the Kernel's Spectrum","created":"2023-07-26","cited_by_count":9,"area":null},{"id":"2402.08010","title":"Which Frequencies do CNNs Need? Emergent Bottleneck Structure in Feature Learning","created":"2024-02-12","cited_by_count":9,"area":null},{"id":"2101.07528","title":"The Unreasonable Effectiveness of Patches in Deep Convolutional Kernels Methods","created":"2021-01-19","cited_by_count":8,"area":null},{"id":"2107.14324","title":"Deep Networks Provably Classify Data on Curves","created":"2021-07-29","cited_by_count":6,"area":null},{"id":"2209.15261","title":"Minimalistic Unsupervised Learning with the Sparse Manifold Transform","created":"2022-09-30","cited_by_count":6,"area":null},{"id":"2305.03531","title":"Random Smoothing Regularization in Kernel Gradient Descent Learning","created":"2023-05-05","cited_by_count":6,"area":null},{"id":"2505.22650","title":"On Learning Verifiers and Implications to Chain-of-Thought Reasoning","created":"2025-05-28","cited_by_count":6,"area":"lr"},{"id":"2508.15127","title":"Towards Source-Free Machine Unlearning","created":"2025-08-20","cited_by_count":6,"area":"safety"},{"id":"2206.08492","title":"TKIL: Tangent Kernel Approach for Class Balanced Incremental Learning","created":"2022-06-17","cited_by_count":5,"area":null},{"id":"2210.11452","title":"Global Convergence of SGD On Two Layer Neural Nets","created":"2022-10-20","cited_by_count":5,"area":null},{"id":"2101.04243","title":"A Convergence Theory Towards Practical Over-parameterized Deep Neural Networks","created":"2021-01-12","cited_by_count":4,"area":null},{"id":"2109.04983","title":"A Neural Tangent Kernel Perspective of Infinite Tree Ensembles","created":"2021-09-10","cited_by_count":4,"area":null},{"id":"2210.09818","title":"Disentangling the Predictive Variance of Deep Ensembles through the Neural Tangent Kernel","created":"2022-10-18","cited_by_count":4,"area":null},{"id":"2406.06504","title":"Equivariant Neural Tangent Kernels","created":"2024-06-10","cited_by_count":4,"area":null},{"id":"2501.02565","title":"Efficient Graph Condensation via Gaussian Process","created":"2025-01-05","cited_by_count":4,"area":null},{"id":"2103.04557","title":"Asymptotics of Ridge Regression in Convolutional Models","created":"2021-03-08","cited_by_count":3,"area":null},{"id":"2105.00262","title":"One-pass Stochastic Gradient Descent in Overparametrized Two-layer Neural Networks","created":"2021-05-01","cited_by_count":3,"area":null},{"id":"2211.13108","title":"Integral Continual Learning Along the Tangent Vector Field of Tasks","created":"2022-11-23","cited_by_count":3,"area":null},{"id":"2309.09258","title":"Global Convergence of SGD For Logistic Loss on Two Layer Neural Nets","created":"2023-09-17","cited_by_count":3,"area":null},{"id":"2309.09814","title":"Convolutional Deep Kernel Machines","created":"2023-09-18","cited_by_count":3,"area":null},{"id":"2506.13714","title":"Understanding Learning Invariance in Deep Linear Networks","created":"2025-06-16","cited_by_count":3,"area":null},{"id":"2112.00265","title":"Training BatchNorm Only in Neural Architecture Search and Beyond","created":"2021-12-01","cited_by_count":2,"area":null},{"id":"2301.00327","title":"Neural Networks with Sparse Activation Induced by Large Bias: Tighter Analysis with Bias-Generalized NTK","created":"2023-01-01","cited_by_count":2,"area":null},{"id":"2405.19995","title":"Symmetries in Overparametrized Neural Networks: A Mean-Field View","created":"2024-05-30","cited_by_count":2,"area":null},{"id":"2103.11558","title":"Weighted Neural Tangent Kernel: A Generalized and Improved Network-Induced Kernel","created":"2021-03-22","cited_by_count":1,"area":null},{"id":"2109.12784","title":"Learning from Few Samples: Transformation-Invariant SVMs with Composition and Locality at Multiple Scales","created":"2021-09-27","cited_by_count":1,"area":null},{"id":"2203.05417","title":"Deep Regression Ensembles","created":"2022-03-10","cited_by_count":1,"area":null},{"id":"2203.16455","title":"Explicitising The Implicit Intrepretability of Deep Neural Networks Via Duality","created":"2022-03-01","cited_by_count":1,"area":null},{"id":"2405.13899","title":"Symmetric Linear Bandits with Hidden Symmetry","created":"2024-05-22","cited_by_count":1,"area":null},{"id":"2503.10428","title":"Langevin Monte-Carlo Provably Learns Depth Two Neural Nets at Any Size and Data","created":"2025-03-13","cited_by_count":1,"area":null},{"id":"2511.05585","title":"Depth-induced NTK: Bridging Over-parameterized Neural Networks and Deep Neural Kernels","created":"2025-11-05","cited_by_count":1,"area":null},{"id":"2603.22155","title":"RAMPAGE: RAndomized Mid-Point for debiAsed Gradient Extrapolation","created":"2026-03-23","cited_by_count":1,"area":null},{"id":"2206.03254","title":"Demystifying the Global Convergence Puzzle of Learning Over-parameterized ReLU Nets in Very High Dimensions","created":"2022-06-05","cited_by_count":0,"area":null},{"id":"2208.03941","title":"Provable Acceleration of Nesterov's Accelerated Gradient Method over Heavy Ball Method in Training Over-Parameterized Neural Networks","created":"2022-08-08","cited_by_count":0,"area":null},{"id":"2211.12345","title":"Understanding Sparse Feature Updates in Deep Networks using Iterative Linearisation","created":"2022-11-22","cited_by_count":0,"area":null},{"id":"2301.11414","title":"A Simple Algorithm For Scaling Up Kernel Methods","created":"2023-01-26","cited_by_count":0,"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":"2310.01739","title":"Randomized Dimension Reduction with Statistical Guarantees","created":"2023-10-03","cited_by_count":0,"area":null},{"id":"2410.06171","title":"Stochastic Kernel Regularisation Improves Generalisation in Deep Kernel Machines","created":"2024-10-08","cited_by_count":0,"area":null},{"id":"2609.03117","title":"Kernel Reboot: Breaking the Boundaries of Neural Tangent Kernels for Neural Fields","created":"2026-09-02","cited_by_count":0,"area":null}],"next_cursor":null}