{"total":134,"rows":[{"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":"2210.15651","title":"Learning Single-Index Models with Shallow Neural Networks","created":"2022-10-27","cited_by_count":92,"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":"2105.05806","title":"High-Dimensional Experimental Design and Kernel Bandits","created":"2021-05-12","cited_by_count":56,"area":null},{"id":"2202.08545","title":"Information Theory with Kernel Methods","created":"2022-02-17","cited_by_count":37,"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":"2403.08160","title":"Asymptotics of Random Feature Regression Beyond the Linear Scaling Regime","created":"2024-03-13","cited_by_count":26,"area":null},{"id":"2107.09597","title":"Positively Weighted Kernel Quadrature via Subsampling","created":"2021-07-20","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":"2201.13055","title":"Nystr\\\"om Kernel Mean Embeddings","created":"2022-01-31","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":"2305.16215","title":"Koopman Kernel Regression","created":"2023-05-25","cited_by_count":22,"area":null},{"id":"2108.03561","title":"Combining machine learning and data assimilation to forecast dynamical systems from noisy partial observations","created":"2021-08-08","cited_by_count":21,"area":null},{"id":"2109.09304","title":"Deformed semicircle law and concentration of nonlinear random matrices for ultra-wide neural networks","created":"2021-09-20","cited_by_count":21,"area":null},{"id":"2408.06526","title":"Operator Learning Using Random Features: A Tool for Scientific Computing","created":"2024-08-12","cited_by_count":21,"area":null},{"id":"2206.04734","title":"Fast Bayesian Inference with Batch Bayesian Quadrature via Kernel Recombination","created":"2022-06-09","cited_by_count":20,"area":null},{"id":"2306.16830","title":"Sampling weights of deep neural networks","created":"2023-06-29","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":"2208.09585","title":"Sharp Analysis of Sketch-and-Project Methods via a Connection to Randomized Singular Value Decomposition","created":"2022-08-20","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":"2301.09517","title":"Sampling-based Nystr\\\"om Approximation and Kernel Quadrature","created":"2023-01-23","cited_by_count":17,"area":null},{"id":"2305.19008","title":"Bottleneck Structure in Learned Features: Low-Dimension vs Regularity Tradeoff","created":"2023-05-30","cited_by_count":17,"area":null},{"id":"2309.14419","title":"On the expressivity of embedding quantum kernels","created":"2023-09-25","cited_by_count":17,"area":null},{"id":"2211.05020","title":"Duality for Neural Networks through Reproducing Kernel Banach Spaces","created":"2022-11-09","cited_by_count":15,"area":null},{"id":"2108.00207","title":"The Separation Capacity of Random Neural Networks","created":"2021-07-31","cited_by_count":14,"area":null},{"id":"2301.11701","title":"TransNet: Transferable Neural Networks for Partial Differential Equations","created":"2023-01-27","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":"2312.08410","title":"Universal approximation property of Banach space-valued random feature models including random neural networks","created":"2023-12-13","cited_by_count":13,"area":null},{"id":"2403.14917","title":"Mean-field Analysis on Two-layer Neural Networks from a Kernel Perspective","created":"2024-03-22","cited_by_count":13,"area":null},{"id":"2202.02877","title":"HARFE: Hard-Ridge Random Feature Expansion","created":"2022-02-06","cited_by_count":12,"area":null},{"id":"2502.10600","title":"Weighted quantization using MMD: From mean field to mean shift via gradient flows","created":"2025-02-14","cited_by_count":12,"area":null},{"id":"2306.03955","title":"Kernel quadrature with randomly pivoted Cholesky","created":"2023-06-06","cited_by_count":11,"area":null},{"id":"2103.04031","title":"Accumulation of Sub-Sampling Matrices with Applications to Statistical Computation","created":"2021-03-06","cited_by_count":10,"area":null},{"id":"2212.05591","title":"Random Feature Models for Learning Interacting Dynamical Systems","created":"2022-12-11","cited_by_count":10,"area":null},{"id":"2311.13548","title":"Efficient Numerical Integration in Reproducing Kernel Hilbert Spaces via Leverage Scores Sampling","created":"2023-11-22","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":"2106.02630","title":"Fundamental tradeoffs between memorization and robustness in random features and neural tangent regimes","created":"2021-06-04","cited_by_count":9,"area":null},{"id":"2201.06487","title":"Minimax risk classifiers with 0-1 loss","created":"2022-01-17","cited_by_count":9,"area":null},{"id":"2206.09186","title":"Causal Inference with Treatment Measurement Error: A Nonparametric Instrumental Variable Approach","created":"2022-06-18","cited_by_count":9,"area":null},{"id":"2411.01036","title":"Computation-Aware Gaussian Processes: Model Selection And Linear-Time Inference","created":"2024-11-01","cited_by_count":9,"area":null},{"id":"2104.07531","title":"On Energy-Based Models with Overparametrized Shallow Neural Networks","created":"2021-04-15","cited_by_count":8,"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":"2401.08260","title":"Fast Kernel Summation in High Dimensions via Slicing and Fourier Transforms","created":"2024-01-16","cited_by_count":8,"area":null},{"id":"2403.12887","title":"Understanding the training of infinitely deep and wide ResNets with Conditional Optimal Transport","created":"2024-03-19","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":"2109.14688","title":"Reliable Estimation of KL Divergence using a Discriminator in Reproducing Kernel Hilbert Space","created":"2021-09-29","cited_by_count":7,"area":null},{"id":"2110.11477","title":"Conditioning of Random Feature Matrices: Double Descent and Generalization Error","created":"2021-10-21","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":"2401.02890","title":"Nonlinear functional regression by functional deep neural network with kernel embedding","created":"2024-01-05","cited_by_count":7,"area":null},{"id":"2410.01316","title":"Fast Summation of Radial Kernels via QMC Slicing","created":"2024-10-02","cited_by_count":7,"area":null},{"id":"2204.06108","title":"SRMD: Sparse Random Mode Decomposition","created":"2022-04-12","cited_by_count":6,"area":null},{"id":"2205.11716","title":"Randomly Initialized One-Layer Neural Networks Make Data Linearly Separable","created":"2022-05-24","cited_by_count":6,"area":null},{"id":"2206.13285","title":"Sum-of-Squares Relaxations for Information Theory and Variational Inference","created":"2022-06-27","cited_by_count":6,"area":null},{"id":"2306.05843","title":"Adaptive Batch Sizes for Active Learning A Probabilistic Numerics Approach","created":"2023-06-09","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":"2101.01137","title":"Gauss-Legendre Features for Gaussian Process Regression","created":"2021-01-04","cited_by_count":5,"area":null},{"id":"2203.12961","title":"Bayesian Deep Learning with Multilevel Trace-class Neural Networks","created":"2022-03-24","cited_by_count":5,"area":null},{"id":"2301.11936","title":"Quantum Ridgelet Transform: Winning Lottery Ticket of Neural Networks with Quantum Computation","created":"2023-01-27","cited_by_count":5,"area":null},{"id":"2302.03459","title":"On the relationship between multivariate splines and infinitely-wide neural networks","created":"2023-02-07","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":"2407.16153","title":"On the Benefits of Rank in Attention Layers","created":"2024-07-23","cited_by_count":5,"area":null},{"id":"2502.18284","title":"Nested Expectations with Kernel Quadrature","created":"2025-02-25","cited_by_count":5,"area":null},{"id":"2605.26900","title":"SPHERE-JEPA: Spherical Prediction with Homogeneous Embeddings","created":"2026-05-26","cited_by_count":5,"area":null},{"id":"2106.09028","title":"Exponential Error Convergence in Data Classification with Optimized Random Features: Acceleration by Quantum Machine Learning","created":"2021-06-16","cited_by_count":4,"area":null},{"id":"2111.03469","title":"Perturbational Complexity by Distribution Mismatch: A Systematic Analysis of Reinforcement Learning in Reproducing Kernel Hilbert Space","created":"2021-11-05","cited_by_count":4,"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":"2302.09703","title":"Reinforcement Learning with Function Approximation: From Linear to Nonlinear","created":"2023-02-20","cited_by_count":4,"area":null},{"id":"2303.02957","title":"Primal and Dual Analysis of Entropic Fictitious Play for Finite-sum Problems","created":"2023-03-06","cited_by_count":4,"area":null},{"id":"2305.16527","title":"When can Regression-Adjusted Control Variates Help? Rare Events, Sobolev Embedding and Minimax Optimality","created":"2023-05-25","cited_by_count":4,"area":null},{"id":"2408.13591","title":"Optimal Kernel Quantile Learning with Random Features","created":"2024-08-24","cited_by_count":4,"area":null},{"id":"2505.08146","title":"Tensor Sketch: Fast and Scalable Polynomial Kernel Approximation","created":"2025-05-13","cited_by_count":4,"area":null},{"id":"2505.14083","title":"Computational Efficiency under Covariate Shift in Kernel Ridge Regression","created":"2025-05-20","cited_by_count":4,"area":null},{"id":"2105.10832","title":"Spectral Pruning for Recurrent Neural Networks","created":"2021-05-23","cited_by_count":3,"area":null},{"id":"2109.10623","title":"Sharp Analysis of Random Fourier Features in Classification","created":"2021-09-22","cited_by_count":3,"area":null},{"id":"2111.10461","title":"Gaussian Process Inference Using Mini-batch Stochastic Gradient Descent: Convergence Guarantees and Empirical Benefits","created":"2021-11-19","cited_by_count":3,"area":null},{"id":"2202.10615","title":"On Average-Case Error Bounds for Kernel-Based Bayesian Quadrature","created":"2022-02-22","cited_by_count":3,"area":null},{"id":"2210.16286","title":"A Functional-Space Mean-Field Theory of Partially-Trained Three-Layer Neural Networks","created":"2022-10-28","cited_by_count":3,"area":null},{"id":"2305.14113","title":"On the Size and Approximation Error of Distilled Sets","created":"2023-05-23","cited_by_count":3,"area":null},{"id":"2309.16846","title":"Optimal Nonlinearities Improve Generalization Performance of Random Features","created":"2023-09-28","cited_by_count":3,"area":null},{"id":"2402.15718","title":"Optimal Rates and Saturation for Noiseless Kernel Ridge Regression","created":"2024-02-24","cited_by_count":3,"area":null},{"id":"2404.12219","title":"A Quadrature Approach for General-Purpose Batch Bayesian Optimization via Probabilistic Lifting","created":"2024-04-18","cited_by_count":3,"area":null},{"id":"2106.02614","title":"Sigma-Delta and Distributed Noise-Shaping Quantization Methods for Random Fourier Features","created":"2021-06-04","cited_by_count":2,"area":null},{"id":"2109.05578","title":"Kernel PCA with the Nystr\\\"om method","created":"2021-09-12","cited_by_count":2,"area":null},{"id":"2310.09437","title":"Signal reconstruction using determinantal sampling","created":"2023-10-13","cited_by_count":2,"area":null},{"id":"2406.18802","title":"All Random Features Representations are Equivalent","created":"2024-06-27","cited_by_count":2,"area":null},{"id":"2408.13231","title":"On the design of scalable, high-precision spherical-radial Fourier features","created":"2024-08-23","cited_by_count":2,"area":null},{"id":"2410.17998","title":"Estimating the Spectral Moments of the Kernel Integral Operator from Finite Sample Matrices","created":"2024-10-23","cited_by_count":2,"area":null},{"id":"2501.02364","title":"Linearly Separable Features in Shallow Nonlinear Networks: Width Scales Polynomially with Intrinsic Data Dimension","created":"2025-01-04","cited_by_count":2,"area":null},{"id":"2505.20754","title":"Stationary MMD Points","created":"2025-05-27","cited_by_count":2,"area":null},{"id":"2507.03340","title":"Degrees of Freedom for Linear Attention: Distilling Softmax Attention with Optimal Feature Efficiency","created":"2025-07-04","cited_by_count":2,"area":null},{"id":"2511.02625","title":"Condition Numbers and Eigenvalue Spectra of Shallow Networks on Spheres","created":"2025-11-04","cited_by_count":2,"area":null},{"id":"2605.14142","title":"To discretize continually: Mean shift interacting particle systems for Bayesian inference","created":"2026-05-13","cited_by_count":2,"area":null},{"id":"2605.31413","title":"Improved Guarantees for Langevin Monte Carlo with Average Smoothness","created":"2026-05-29","cited_by_count":2,"area":null},{"id":"2211.08036","title":"Provably Reliable Large-Scale Sampling from Gaussian Processes","created":"2022-11-15","cited_by_count":1,"area":null},{"id":"2302.00205","title":"Gradient Descent in Neural Networks as Sequential Learning in RKBS","created":"2023-02-01","cited_by_count":1,"area":null},{"id":"2306.02833","title":"The $L^\\infty$ Learnability of Reproducing Kernel Hilbert Spaces","created":"2023-06-05","cited_by_count":1,"area":null},{"id":"2310.06483","title":"Variance Reduced Online Gradient Descent for Kernelized Pairwise Learning with Limited Memory","created":"2023-10-10","cited_by_count":1,"area":null},{"id":"2310.14768","title":"Policy Gradient with Kernel Quadrature","created":"2023-10-23","cited_by_count":1,"area":null},{"id":"2402.11736","title":"Monte Carlo with kernel-based Gibbs measures: Guarantees for probabilistic herding","created":"2024-02-18","cited_by_count":1,"area":null},{"id":"2411.19468","title":"Learning Expressive Random Feature Models via Parametrized Activations","created":"2024-11-29","cited_by_count":1,"area":null}],"next_cursor":"100"}