{"total":155,"rows":[{"id":"2006.13198","title":"Spectral Bias and Task-Model Alignment Explain Generalization in Kernel Regression and Infinitely Wide Neural Networks","created":"2020-06-23","cited_by_count":166,"area":"alignment"},{"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":"2302.11055","title":"SGD learning on neural networks: leap complexity and saddle-to-saddle dynamics","created":"2023-02-21","cited_by_count":143,"area":null},{"id":"2402.01868","title":"Challenges in Training PINNs: A Loss Landscape Perspective","created":"2024-02-02","cited_by_count":113,"area":null},{"id":"2109.07740","title":"Scaling Laws for Neural Machine Translation","created":"2021-09-16","cited_by_count":111,"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":"2310.06110","title":"Grokking as the Transition from Lazy to Rich Training Dynamics","created":"2023-10-09","cited_by_count":108,"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":"2405.14622","title":"Calibrated Self-Rewarding Vision Language Models","created":"2024-05-23","cited_by_count":78,"area":"mllm"},{"id":"2303.00055","title":"Learning time-scales in two-layers neural networks","created":"2023-02-28","cited_by_count":57,"area":null},{"id":"2405.00592","title":"Scaling and renormalization in high-dimensional regression","created":"2024-05-01","cited_by_count":50,"area":null},{"id":"2102.02410","title":"A Local Convergence Theory for Mildly Over-Parameterized Two-Layer Neural Network","created":"2021-02-04","cited_by_count":47,"area":null},{"id":"2406.01581","title":"Neural network learns low-dimensional polynomials with SGD near the information-theoretic limit","created":"2024-06-03","cited_by_count":46,"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":"2302.00375","title":"Bayes-optimal Learning of Deep Random Networks of Extensive-width","created":"2023-02-01","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":"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,"area":null},{"id":"2205.10217","title":"Memorization and Optimization in Deep Neural Networks with Minimum Over-parameterization","created":"2022-05-20","cited_by_count":36,"area":null},{"id":"2306.04073","title":"Patch-level Routing in Mixture-of-Experts is Provably Sample-efficient for Convolutional Neural Networks","created":"2023-06-07","cited_by_count":35,"area":"moe"},{"id":"2104.04244","title":"How rotational invariance of common kernels prevents generalization in high dimensions","created":"2021-04-09","cited_by_count":32,"area":null},{"id":"2411.02544","title":"Pretrained transformer efficiently learns low-dimensional target functions in-context","created":"2024-11-04","cited_by_count":31,"area":null},{"id":"2106.03212","title":"Towards an Understanding of Benign Overfitting in Neural Networks","created":"2021-06-06","cited_by_count":30,"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":"2108.04190","title":"On the Power of Differentiable Learning versus PAC and SQ Learning","created":"2021-08-09","cited_by_count":28,"area":null},{"id":"2205.06308","title":"An Equivalence Principle for the Spectrum of Random Inner-Product Kernel Matrices with Polynomial Scalings","created":"2022-05-12","cited_by_count":27,"area":null},{"id":"2312.15995","title":"Generalization in Kernel Regression Under Realistic Assumptions","created":"2023-12-26","cited_by_count":27,"area":null},{"id":"2305.14077","title":"Mind the spikes: Benign overfitting of kernels and neural networks in fixed dimension","created":"2023-05-23","cited_by_count":26,"area":null},{"id":"2202.12482","title":"Sparse Neural Additive Model: Interpretable Deep Learning with Feature Selection via Group Sparsity","created":"2022-02-25","cited_by_count":25,"area":null},{"id":"2212.13881","title":"Mechanism of feature learning in deep fully connected networks and kernel machines that recursively learn features","created":"2022-12-28","cited_by_count":25,"area":null},{"id":"2305.17170","title":"Error Bounds for Learning with Vector-Valued Random Features","created":"2023-05-26","cited_by_count":23,"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":"2205.14846","title":"Precise Learning Curves and Higher-Order Scaling Limits for Dot Product Kernel Regression","created":"2022-05-30","cited_by_count":22,"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":"2302.06210","title":"Precise Asymptotic Analysis of Deep Random Feature Models","created":"2023-02-13","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":"2206.10451","title":"Winning the Lottery Ahead of Time: Efficient Early Network Pruning","created":"2022-06-21","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":"2106.06573","title":"Understanding Deflation Process in Over-parametrized Tensor Decomposition","created":"2021-06-11","cited_by_count":20,"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":"2205.06798","title":"Sharp Asymptotics of Kernel Ridge Regression Beyond the Linear Regime","created":"2022-05-13","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":"2410.14148","title":"Fine-Grained Verifiers: Preference Modeling as Next-token Prediction in Vision-Language Alignment","created":"2024-10-18","cited_by_count":19,"area":"alignment"},{"id":"2208.03113","title":"On the non-universality of deep learning: quantifying the cost of symmetry","created":"2022-08-05","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":"2112.05611","title":"Eigenspace Restructuring: a Principle of Space and Frequency in Neural Networks","created":"2021-12-10","cited_by_count":17,"area":null},{"id":"2111.05987","title":"Tight bounds for minimum l1-norm interpolation of noisy data","created":"2021-11-10","cited_by_count":16,"area":null},{"id":"2303.15809","title":"Kernel interpolation generalizes poorly","created":"2023-03-28","cited_by_count":16,"area":null},{"id":"2107.04518","title":"Optimal Gradient-based Algorithms for Non-concave Bandit Optimization","created":"2021-07-09","cited_by_count":15,"area":null},{"id":"2108.02883","title":"Interpolation can hurt robust generalization even when there is no noise","created":"2021-08-05","cited_by_count":15,"area":null},{"id":"2410.05464","title":"Progressive distillation induces an implicit curriculum","created":"2024-10-07","cited_by_count":15,"area":null},{"id":"2111.05198","title":"Harmless interpolation in regression and classification with structured features","created":"2021-11-09","cited_by_count":14,"area":null},{"id":"2103.04554","title":"Exact Gap between Generalization Error and Uniform Convergence in Random Feature Models","created":"2021-03-08","cited_by_count":13,"area":null},{"id":"2103.05243","title":"On the Generalization Power of Overfitted Two-Layer Neural Tangent Kernel Models","created":"2021-03-09","cited_by_count":13,"area":null},{"id":"2206.03688","title":"Identifying good directions to escape the NTK regime and efficiently learn low-degree plus sparse polynomials","created":"2022-06-08","cited_by_count":13,"area":null},{"id":"2302.07937","title":"The Expressive Power of Tuning Only the Normalization Layers","created":"2023-02-15","cited_by_count":13,"area":null},{"id":"2307.05635","title":"Fundamental limits of overparametrized shallow neural networks for supervised learning","created":"2023-07-11","cited_by_count":13,"area":null},{"id":"2301.13371","title":"Demystifying Disagreement-on-the-Line in High Dimensions","created":"2023-01-31","cited_by_count":12,"area":null},{"id":"2105.06569","title":"The Dynamics of Gradient Descent for Overparametrized Neural Networks","created":"2021-05-13","cited_by_count":11,"area":null},{"id":"2305.12100","title":"How Spurious Features Are Memorized: Precise Analysis for Random and NTK Features","created":"2023-05-20","cited_by_count":11,"area":null},{"id":"2309.04268","title":"Optimal Rate of Kernel Regression in Large Dimensions","created":"2023-09-08","cited_by_count":11,"area":null},{"id":"2401.01599","title":"Generalization Error Curves for Analytic Spectral Algorithms under Power-law Decay","created":"2024-01-03","cited_by_count":11,"area":null},{"id":"2109.06915","title":"Reconstruction on Trees and Low-Degree Polynomials","created":"2021-09-14","cited_by_count":10,"area":null},{"id":"2205.14818","title":"Excess Risk of Two-Layer ReLU Neural Networks in Teacher-Student Settings and its Superiority to Kernel Methods","created":"2022-05-30","cited_by_count":10,"area":"distill"},{"id":"2301.07605","title":"Strong inductive biases provably prevent harmless interpolation","created":"2023-01-18","cited_by_count":10,"area":null},{"id":"2402.05271","title":"Feature learning as alignment: a structural property of gradient descent in non-linear neural networks","created":"2024-02-07","cited_by_count":10,"area":null},{"id":"2510.04780","title":"Kernel ridge regression under power-law data: spectrum and generalization","created":"2025-10-06","cited_by_count":10,"area":null},{"id":"2107.06466","title":"Going Beyond Linear RL: Sample Efficient Neural Function Approximation","created":"2021-07-14","cited_by_count":9,"area":null},{"id":"2209.02525","title":"Generalisation under gradient descent via deterministic PAC-Bayes","created":"2022-09-06","cited_by_count":9,"area":null},{"id":"2311.13774","title":"Learning Hierarchical Polynomials with Three-Layer Neural Networks","created":"2023-11-23","cited_by_count":9,"area":null},{"id":"2404.12597","title":"The phase diagram of kernel interpolation in large dimensions","created":"2024-04-19","cited_by_count":9,"area":null},{"id":"2505.24849","title":"Statistical mechanics of extensive-width Bayesian neural networks near interpolation","created":"2025-05-30","cited_by_count":9,"area":null},{"id":"2106.03589","title":"Nonparametric adaptive control and prediction: theory and randomized algorithms","created":"2021-06-07","cited_by_count":8,"area":null},{"id":"2307.10870","title":"Nonlinear Meta-Learning Can Guarantee Faster Rates","created":"2023-07-20","cited_by_count":8,"area":null},{"id":"2402.01089","title":"No Free Prune: Information-Theoretic Barriers to Pruning at Initialization","created":"2024-02-02","cited_by_count":8,"area":null},{"id":"2404.18769","title":"Learning with Norm Constrained, Over-parameterized, Two-layer Neural Networks","created":"2024-04-29","cited_by_count":8,"area":null},{"id":"2108.04964","title":"A spectral-based analysis of the separation between two-layer neural networks and linear methods","created":"2021-08-10","cited_by_count":7,"area":null},{"id":"2211.06077","title":"Overparameterized random feature regression with nearly orthogonal data","created":"2022-11-11","cited_by_count":7,"area":null},{"id":"2305.00979","title":"Spectral clustering in the Gaussian mixture block model","created":"2023-04-29","cited_by_count":7,"area":null},{"id":"2409.03891","title":"Overfitting Behaviour of Gaussian Kernel Ridgeless Regression: Varying Bandwidth or Dimensionality","created":"2024-09-05","cited_by_count":7,"area":null},{"id":"2103.14723","title":"Lower Bounds on the Generalization Error of Nonlinear Learning Models","created":"2021-03-26","cited_by_count":6,"area":null},{"id":"2107.14324","title":"Deep Networks Provably Classify Data on Curves","created":"2021-07-29","cited_by_count":6,"area":null},{"id":"2206.02047","title":"On the Generalization Power of the Overfitted Three-Layer Neural Tangent Kernel Model","created":"2022-06-04","cited_by_count":6,"area":null},{"id":"2402.10164","title":"Random features and polynomial rules","created":"2024-02-15","cited_by_count":6,"area":null},{"id":"2505.03577","title":"Information-theoretic reduction of deep neural networks to linear models in the overparametrized proportional regime","created":"2025-05-06","cited_by_count":6,"area":null},{"id":"2103.15996","title":"Minimum complexity interpolation in random features models","created":"2021-03-30","cited_by_count":5,"area":null},{"id":"2110.06910","title":"On the Double Descent of Random Features Models Trained with SGD","created":"2021-10-13","cited_by_count":5,"area":null},{"id":"2201.00073","title":"Kernel Two-Sample Tests in High Dimension: Interplay Between Moment Discrepancy and Dimension-and-Sample Orders","created":"2021-12-31","cited_by_count":5,"area":null},{"id":"2306.13185","title":"An Agnostic View on the Cost of Overfitting in (Kernel) Ridge Regression","created":"2023-06-22","cited_by_count":5,"area":null},{"id":"2402.02969","title":"Towards Understanding the Word Sensitivity of Attention Layers: A Study via Random Features","created":"2024-02-05","cited_by_count":5,"area":null},{"id":"2602.10867","title":"Deep Learning of Compositional Targets with Hierarchical Spectral Methods","created":"2026-02-11","cited_by_count":5,"area":null},{"id":"2206.01332","title":"Optimal Activation Functions for the Random Features Regression Model","created":"2022-05-31","cited_by_count":4,"area":null},{"id":"2208.08835","title":"Differentiable Architecture Search with Random Features","created":"2022-08-18","cited_by_count":4,"area":null},{"id":"2305.00995","title":"Towards a Phenomenological Understanding of Neural Networks: Data","created":"2023-05-01","cited_by_count":4,"area":null},{"id":"2305.14689","title":"Least Squares Regression Can Exhibit Under-Parameterized Double Descent","created":"2023-05-24","cited_by_count":4,"area":null},{"id":"2402.07025","title":"Generalization Error of Graph Neural Networks in the Mean-field Regime","created":"2024-02-10","cited_by_count":4,"area":null},{"id":"2406.03171","title":"High-Dimensional Kernel Methods under Covariate Shift: Data-Dependent Implicit Regularization","created":"2024-06-05","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}],"next_cursor":"100"}