{"total":109,"rows":[{"id":"2205.00403","title":"A Simple Approach to Improve Single-Model Deep Uncertainty via Distance-Awareness","created":"2022-05-01","cited_by_count":49,"area":null},{"id":"2107.09597","title":"Positively Weighted Kernel Quadrature via Subsampling","created":"2021-07-20","cited_by_count":25,"area":null},{"id":"2110.04367","title":"Hybrid Random Features","created":"2021-10-08","cited_by_count":25,"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":"2306.16830","title":"Sampling weights of deep neural networks","created":"2023-06-29","cited_by_count":20,"area":null},{"id":"2305.00156","title":"Taming graph kernels with random features","created":"2023-04-29","cited_by_count":17,"area":null},{"id":"2110.08323","title":"On Learning the Transformer Kernel","created":"2021-10-15","cited_by_count":15,"area":null},{"id":"2306.14809","title":"Tanimoto Random Features for Scalable Molecular Machine Learning","created":"2023-06-26","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":"2109.01545","title":"Large-Scale Learning with Fourier Features and Tensor Decompositions","created":"2021-09-03","cited_by_count":14,"area":null},{"id":"2112.00423","title":"Controlling Wasserstein Distances by Kernel Norms with Application to Compressive Statistical Learning","created":"2021-12-01","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":"2201.08712","title":"Improved Random Features for Dot Product Kernels","created":"2022-01-21","cited_by_count":12,"area":null},{"id":"2109.00212","title":"Diverse Sample Generation: Pushing the Limit of Generative Data-free Quantization","created":"2021-09-01","cited_by_count":11,"area":null},{"id":"2202.01397","title":"Learning with Asymmetric Kernels: Least Squares and Feature Interpretation","created":"2022-02-03","cited_by_count":11,"area":null},{"id":"2201.02880","title":"Attention-based Random Forest and Contamination Model","created":"2022-01-08","cited_by_count":10,"area":null},{"id":"2212.04604","title":"Localized Contrastive Learning on Graphs","created":"2022-12-08","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":"2402.03994","title":"Efficient Sketches for Training Data Attribution and Studying the Loss Landscape","created":"2024-02-06","cited_by_count":10,"area":null},{"id":"2204.06935","title":"Concentration of Random Feature Matrices in High-Dimensions","created":"2022-04-14","cited_by_count":9,"area":null},{"id":"2301.13856","title":"Simplex Random Features","created":"2023-01-31","cited_by_count":9,"area":null},{"id":"2305.12470","title":"Quasi-Monte Carlo Graph Random Features","created":"2023-05-21","cited_by_count":9,"area":null},{"id":"2311.12214","title":"Random Fourier Signature Features","created":"2023-11-20","cited_by_count":9,"area":null},{"id":"2406.04657","title":"From Spikes to Heavy Tails: Unveiling the Spectral Evolution of Neural Networks","created":"2024-06-07","cited_by_count":9,"area":null},{"id":"2201.08082","title":"Kernel Methods and Multi-layer Perceptrons Learn Linear Models in High Dimensions","created":"2022-01-20","cited_by_count":8,"area":null},{"id":"2310.00987","title":"A Theoretical Analysis of the Test Error of Finite-Rank Kernel Ridge Regression","created":"2023-10-02","cited_by_count":8,"area":null},{"id":"2505.18976","title":"GraSS: Scalable Data Attribution with Gradient Sparsification and Sparse Projection","created":"2025-05-25","cited_by_count":8,"area":null},{"id":"2110.01899","title":"Random matrices in service of ML footprint: ternary random features with no performance loss","created":"2021-10-05","cited_by_count":7,"area":null},{"id":"2209.08461","title":"Random Fourier Features for Asymmetric Kernels","created":"2022-09-18","cited_by_count":7,"area":null},{"id":"2407.00584","title":"Hyperparameter Optimization for Randomized Algorithms: A Case Study on Random Features","created":"2024-06-30","cited_by_count":7,"area":null},{"id":"2204.05667","title":"Local Random Feature Approximations of the Gaussian Kernel","created":"2022-04-12","cited_by_count":6,"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":"2207.05724","title":"AGBoost: Attention-based Modification of Gradient Boosting Machine","created":"2022-07-12","cited_by_count":5,"area":null},{"id":"2210.14796","title":"AD-DMKDE: Anomaly Detection through Density Matrices and Fourier Features","created":"2022-10-26","cited_by_count":5,"area":null},{"id":"2405.15310","title":"Spectraformer: A Unified Random Feature Framework for Transformer","created":"2024-05-24","cited_by_count":5,"area":null},{"id":"2409.12865","title":"KnowFormer: Revisiting Transformers for Knowledge Graph Reasoning","created":"2024-09-19","cited_by_count":5,"area":"lr"},{"id":"2503.00300","title":"Cauchy Random Features for Operator Learning in Sobolev Space","created":"2025-03-01","cited_by_count":5,"area":null},{"id":"2507.05478","title":"Dynamic Regret Reduces to Kernelized Static Regret","created":"2025-07-07","cited_by_count":5,"area":null},{"id":"2106.02755","title":"Kernel approximation on algebraic varieties","created":"2021-06-04","cited_by_count":4,"area":null},{"id":"2204.07293","title":"Towards a Unified Framework for Uncertainty-aware Nonlinear Variable Selection with Theoretical Guarantees","created":"2022-04-15","cited_by_count":4,"area":null},{"id":"2207.04293","title":"Attention and Self-Attention in Random Forests","created":"2022-07-09","cited_by_count":4,"area":null},{"id":"2310.09127","title":"On Generalization Bounds for Projective Clustering","created":"2023-10-13","cited_by_count":4,"area":null},{"id":"2311.04686","title":"Robust and Communication-Efficient Federated Domain Adaptation via Random Features","created":"2023-11-08","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":"2109.10623","title":"Sharp Analysis of Random Fourier Features in Classification","created":"2021-09-22","cited_by_count":3,"area":null},{"id":"2206.08054","title":"Generalized Leverage Scores: Geometric Interpretation and Applications","created":"2022-06-16","cited_by_count":3,"area":null},{"id":"2210.05206","title":"Kernelized multi-graph matching","created":"2022-10-11","cited_by_count":3,"area":null},{"id":"2211.04226","title":"Gradient-enhanced deep neural network approximations","created":"2022-11-08","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":"2407.00765","title":"Structured and Balanced Multi-Component and Multi-Layer Neural Networks","created":"2024-06-30","cited_by_count":3,"area":null},{"id":"2408.00549","title":"Learning to Embed Distributions via Maximum Kernel Entropy","created":"2024-08-01","cited_by_count":3,"area":null},{"id":"2410.08557","title":"MUSO: Achieving Exact Machine Unlearning in Over-Parameterized Regimes","created":"2024-10-11","cited_by_count":3,"area":"safety"},{"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":"2210.00244","title":"On The Relative Error of Random Fourier Features for Preserving Kernel Distance","created":"2022-10-01","cited_by_count":2,"area":null},{"id":"2210.02558","title":"Improved Anomaly Detection by Using the Attention-Based Isolation Forest","created":"2022-10-05","cited_by_count":2,"area":null},{"id":"2311.00902","title":"Data-Driven Model Selections of Second-Order Particle Dynamics via Integrating Gaussian Processes with Low-Dimensional Interacting Structures","created":"2023-11-01","cited_by_count":2,"area":null},{"id":"2402.00645","title":"Spectrally Transformed Kernel Regression","created":"2024-02-01","cited_by_count":2,"area":null},{"id":"2404.03050","title":"ANOVA-boosting for Random Fourier Features","created":"2024-04-03","cited_by_count":2,"area":null},{"id":"2405.16541","title":"Variance-Reducing Couplings for Random Features","created":"2024-05-26","cited_by_count":2,"area":null},{"id":"2408.03626","title":"On the choice of the non-trainable internal weights in random feature maps","created":"2024-08-07","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":"2410.10641","title":"Echo State Networks for Spatio-Temporal Area-Level Data","created":"2024-10-14","cited_by_count":2,"area":null},{"id":"2411.06848","title":"Generative Feature Training of Thin 2-Layer Networks","created":"2024-11-11","cited_by_count":2,"area":null},{"id":"2412.04785","title":"Differentially Private Random Feature Model","created":"2024-12-06","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":"2201.02958","title":"Smooth Nested Simulation: Bridging Cubic and Square Root Convergence Rates in High Dimensions","created":"2022-01-09","cited_by_count":1,"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":"2211.08525","title":"LEAN-DMKDE: Quantum Latent Density Estimation for Anomaly Detection","created":"2022-11-15","cited_by_count":1,"area":null},{"id":"2302.11174","title":"Error Estimation for Random Fourier Features","created":"2023-02-22","cited_by_count":1,"area":null},{"id":"2310.07370","title":"Orthogonal Random Features: Explicit Forms and Sharp Inequalities","created":"2023-10-11","cited_by_count":1,"area":null},{"id":"2405.06869","title":"Sharpness-Aware Minimization for Evolutionary Feature Construction in Regression","created":"2024-05-11","cited_by_count":1,"area":null},{"id":"2405.07791","title":"Decentralized Kernel Ridge Regression Based on Data-Dependent Random Feature","created":"2024-05-13","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},{"id":"2502.15575","title":"Feature maps for the Laplacian kernel and its generalizations","created":"2025-02-21","cited_by_count":1,"area":null},{"id":"2504.05490","title":"Optimal Bayesian Affine Estimator and Active Learning for the Wiener Model","created":"2025-04-07","cited_by_count":1,"area":null},{"id":"2505.15284","title":"Kernel PCA for Out-of-Distribution Detection: Non-Linear Kernel Selection and Approximation","created":"2025-05-21","cited_by_count":1,"area":null},{"id":"2506.03779","title":"Position: Quantum Kernel Machines Should Move Beyond Scalar-Valued Kernels to Realize Their Potential","created":"2025-06-04","cited_by_count":1,"area":null},{"id":"2511.03824","title":"Sketch-Augmented Features Improve Learning Long-Range Dependencies in Graph Neural Networks","created":"2025-11-05","cited_by_count":1,"area":null},{"id":"2601.17562","title":"Sparse RBF Networks for PDEs and nonlocal equations: function space theory, operator calculus, and training algorithms","created":"2026-01-24","cited_by_count":1,"area":null},{"id":"2602.03797","title":"Manifold Random Features","created":"2026-02-03","cited_by_count":1,"area":null},{"id":"2603.23868","title":"MLE-UVAD: Minimal Latent Entropy Autoencoder for Fully Unsupervised Video Anomaly Detection","created":"2026-03-25","cited_by_count":1,"area":null},{"id":"2605.22275","title":"Adaptive Measurement Allocation for Learning Kernelized SVMs Under Noisy Observations","created":"2026-05-21","cited_by_count":1,"area":null},{"id":"2607.18554","title":"Scalable Policy Optimization for Networked Multi-Agent Reinforcement Learning with Continuous State-Action Spaces","created":"2026-07-20","cited_by_count":1,"area":null},{"id":"2106.13066","title":"Shallow Representation is Deep: Learning Uncertainty-aware and Worst-case Random Feature Dynamics","created":"2021-06-24","cited_by_count":0,"area":null},{"id":"2108.08605","title":"Fast Newton method solving KLR based on Multilevel Circulant Matrix with log-linear complexity","created":"2021-08-19","cited_by_count":0,"area":null},{"id":"2201.09223","title":"A Generalized Weighted Optimization Method for Computational Learning and Inversion","created":"2022-01-23","cited_by_count":0,"area":null},{"id":"2210.05168","title":"LARF: Two-level Attention-based Random Forests with a Mixture of Contamination Models","created":"2022-10-11","cited_by_count":0,"area":null},{"id":"2211.14062","title":"M$^2$M: A general method to perform various data analysis tasks from a differentially private sketch","created":"2022-11-25","cited_by_count":0,"area":null},{"id":"2302.11032","title":"Boosting Nystr\\\"{o}m Method","created":"2023-02-21","cited_by_count":0,"area":null},{"id":"2305.09385","title":"Lp- and Risk Consistency of Localized SVMs","created":"2023-05-16","cited_by_count":0,"area":null},{"id":"2402.04794","title":"Scalable Multi-view Clustering via Explicit Kernel Features Maps","created":"2024-02-07","cited_by_count":0,"area":null},{"id":"2406.00438","title":"Stein Random Feature Regression","created":"2024-06-01","cited_by_count":0,"area":null},{"id":"2408.07623","title":"Latent Anomaly Detection Through Density Matrices","created":"2024-08-14","cited_by_count":0,"area":null},{"id":"2411.03375","title":"Kernel Approximation using Analog In-Memory Computing","created":"2024-11-05","cited_by_count":0,"area":null},{"id":"2501.07991","title":"Training Hybrid Neural Networks with Multimode Optical Nonlinearities Using Digital Twins","created":"2025-01-14","cited_by_count":0,"area":null},{"id":"2502.04323","title":"The Uniformly Rotated Mondrian Kernel","created":"2025-02-06","cited_by_count":0,"area":null},{"id":"2503.06041","title":"Randomized Quasi-Monte Carlo Features for Kernel Approximation","created":"2025-03-08","cited_by_count":0,"area":null},{"id":"2503.12456","title":"Nonlinear Principal Component Analysis with Random Bernoulli Features for Process Monitoring","created":"2025-03-16","cited_by_count":0,"area":null}],"next_cursor":"100"}