{"total":91,"rows":[{"id":"2103.02143","title":"Random Feature Attention","created":"2021-03-03","cited_by_count":354,"area":null},{"id":"2207.02505","title":"Pure Transformers are Powerful Graph Learners","created":"2022-07-06","cited_by_count":188,"area":null},{"id":"2204.00595","title":"Monarch: Expressive Structured Matrices for Efficient and Accurate Training","created":"2022-04-01","cited_by_count":106,"area":null},{"id":"2103.13076","title":"Finetuning Pretrained Transformers into RNNs","created":"2021-03-24","cited_by_count":96,"area":null},{"id":"2202.02195","title":"Deep End-to-end Causal Inference","created":"2022-02-04","cited_by_count":95,"area":null},{"id":"2108.08842","title":"EDEN: Communication-Efficient and Robust Distributed Mean Estimation for Federated Learning","created":"2021-08-19","cited_by_count":55,"area":null},{"id":"2406.03482","title":"QJL: 1-Bit Quantized JL Transform for KV Cache Quantization with Zero Overhead","created":"2024-06-05","cited_by_count":52,"area":"inference"},{"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":"2210.12642","title":"Accelerated Linearized Laplace Approximation for Bayesian Deep Learning","created":"2022-10-23","cited_by_count":28,"area":null},{"id":"2205.00165","title":"NeuralEF: Deconstructing Kernels by Deep Neural Networks","created":"2022-04-30","cited_by_count":27,"area":null},{"id":"2110.04367","title":"Hybrid Random Features","created":"2021-10-08","cited_by_count":25,"area":null},{"id":"2102.04394","title":"Learning with Density Matrices and Random Features","created":"2021-02-08","cited_by_count":17,"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":"2310.13220","title":"Towards Understanding How Transformers Learn In-context Through a Representation Learning Lens","created":"2023-10-20","cited_by_count":15,"area":null},{"id":"2501.11175","title":"ProKeR: A Kernel Perspective on Few-Shot Adaptation of Large Vision-Language Models","created":"2025-01-19","cited_by_count":15,"area":"mllm"},{"id":"2201.08712","title":"Improved Random Features for Dot Product Kernels","created":"2022-01-21","cited_by_count":12,"area":null},{"id":"2502.07861","title":"Streaming Attention Approximation via Discrepancy Theory","created":"2025-02-11","cited_by_count":11,"area":null},{"id":"2204.05424","title":"A Call for Clarity in Beam Search: How It Works and When It Stops","created":"2022-04-11","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":"2310.04859","title":"General Graph Random Features","created":"2023-10-07","cited_by_count":10,"area":null},{"id":"2203.01599","title":"Uniform Approximations for Randomized Hadamard Transforms with Applications","created":"2022-03-03","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":"2310.13225","title":"Scalable Neural Network Kernels","created":"2023-10-20","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":"2106.05992","title":"Scalable Variational Gaussian Processes via Harmonic Kernel Decomposition","created":"2021-06-10","cited_by_count":8,"area":null},{"id":"2204.06517","title":"Learning Self-Modulating Attention in Continuous Time Space with Applications to Sequential Recommendation","created":"2022-03-30","cited_by_count":8,"area":null},{"id":"2506.08997","title":"SDTagNet: Leveraging Text-Annotated Navigation Maps for Online HD Map Construction","created":"2025-06-10","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":"2205.13341","title":"QUIC-FL: Quick Unbiased Compression for Federated Learning","created":"2022-05-26","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":"2204.05667","title":"Local Random Feature Approximations of the Gaussian Kernel","created":"2022-04-12","cited_by_count":6,"area":null},{"id":"2310.04854","title":"Repelling Random Walks","created":"2023-10-07","cited_by_count":6,"area":null},{"id":"2303.12678","title":"Uni-Fusion: Universal Continuous Mapping","created":"2023-03-22","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":"2509.03691","title":"Graph Random Features for Scalable Gaussian Processes","created":"2025-09-03","cited_by_count":5,"area":null},{"id":"2203.12644","title":"Linearizing Transformer with Key-Value Memory","created":"2022-03-23","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":"2501.00712","title":"Rethinking Addressing in Language Models via Contexualized Equivariant Positional Encoding","created":"2025-01-01","cited_by_count":4,"area":"lr"},{"id":"2102.04353","title":"Unlocking Pixels for Reinforcement Learning via Implicit Attention","created":"2021-02-08","cited_by_count":3,"area":null},{"id":"2401.14557","title":"Comparison of Reservoir Computing topologies using the Recurrent Kernel approach","created":"2024-01-25","cited_by_count":3,"area":null},{"id":"2407.21091","title":"The Stochastic Conjugate Subgradient Algorithm For Kernel Support Vector Machines","created":"2024-07-30","cited_by_count":3,"area":null},{"id":"2505.13556","title":"Learning collision risk proactively from naturalistic driving data at scale","created":"2025-05-19","cited_by_count":3,"area":null},{"id":"2105.03781","title":"MetaKernel: Learning Variational Random Features with Limited Labels","created":"2021-05-08","cited_by_count":2,"area":null},{"id":"2302.03294","title":"Linear-scaling kernels for protein sequences and small molecules outperform deep learning while providing uncertainty quantitation and improved interpretability","created":"2023-02-07","cited_by_count":2,"area":null},{"id":"2310.14544","title":"Trigonometric Quadrature Fourier Features for Scalable Gaussian Process Regression","created":"2023-10-23","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":"2408.13231","title":"On the design of scalable, high-precision spherical-radial Fourier features","created":"2024-08-23","cited_by_count":2,"area":null},{"id":"2503.20488","title":"Adaptive Local Clustering over Attributed Graphs","created":"2025-03-26","cited_by_count":2,"area":null},{"id":"2507.01241","title":"Beyond First-Order: Training LLMs with Stochastic Conjugate Subgradients and AdamW","created":"2025-07-01","cited_by_count":2,"area":null},{"id":"2508.03222","title":"Revisiting Deep Information Propagation: Fractal Frontier and Finite-size Effects","created":"2025-08-05","cited_by_count":2,"area":null},{"id":"2508.17388","title":"Effective Clustering for Large Multi-Relational Graphs","created":"2025-08-24","cited_by_count":2,"area":null},{"id":"2601.22563","title":"EUGens: Efficient, Unified, and General Dense Layers","created":"2026-01-30","cited_by_count":2,"area":null},{"id":"2604.23418","title":"Approximating Uniform Random Rotations by Two-Stage Structured Hadamard Rotations in High Dimensions","created":"2026-04-25","cited_by_count":2,"area":null},{"id":"2101.05239","title":"Denoising Score Matching with Random Fourier Features","created":"2021-01-13","cited_by_count":1,"area":null},{"id":"2104.06204","title":"Towards Unbiased Random Features with Lower Variance For Stationary Indefinite Kernels","created":"2021-04-13","cited_by_count":1,"area":null},{"id":"2109.14198","title":"Breaking the curse of dimensionality with Isolation Kernel","created":"2021-09-29","cited_by_count":1,"area":null},{"id":"2203.07411","title":"On Connecting Deep Trigonometric Networks with Deep Gaussian Processes: Covariance, Expressivity, and Neural Tangent Kernel","created":"2022-03-14","cited_by_count":1,"area":null},{"id":"2303.05018","title":"Improved Regret Bounds for Online Kernel Selection under Bandit Feedback","created":"2023-03-09","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":"2311.04673","title":"Compressive Recovery of Sparse Precision Matrices","created":"2023-11-08","cited_by_count":1,"area":null},{"id":"2502.05301","title":"Decentralized Online Ensembles of Gaussian Processes for Multi-Agent Systems","created":"2025-02-07","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":"2602.03797","title":"Manifold Random Features","created":"2026-02-03","cited_by_count":1,"area":null},{"id":"2605.01263","title":"New Bounds for Kernel Sums via Fast Spherical Embeddings","created":"2026-05-02","cited_by_count":1,"area":null},{"id":"2605.05743","title":"Fourier Feature Methods for Nonlinear Causal Discovery: FFML Scoring, TRFF Scoring, and FFCI Testing in Mixed Data","created":"2026-05-07","cited_by_count":1,"area":null},{"id":"2101.07415","title":"ES-ENAS: Efficient Evolutionary Optimization for Large Hybrid Search Spaces","created":"2021-01-19","cited_by_count":0,"area":null},{"id":"2106.06097","title":"Neural Optimization Kernel: Towards Robust Deep Learning","created":"2021-06-11","cited_by_count":0,"area":null},{"id":"2110.15440","title":"HD-cos Networks: Efficient Neural Architectures for Secure Multi-Party Computation","created":"2021-10-28","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":"2410.09771","title":"EUGens: Efficient, Unified, and General Dense Layers","created":"2024-10-13","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":"2502.00585","title":"Converting Transformers into DGNNs Form","created":"2025-02-01","cited_by_count":0,"area":null},{"id":"2508.15552","title":"Sequential Adaptive Priors for Orthogonal Functions","created":"2025-08-21","cited_by_count":0,"area":null},{"id":"2509.25228","title":"Random Projection Flows for Efficient Manifold Density Estimation","created":"2025-09-24","cited_by_count":0,"area":null},{"id":"2602.12703","title":"SWING: Unlocking Implicit Graph Representations for Graph Random Features","created":"2026-02-13","cited_by_count":0,"area":null},{"id":"2602.15711","title":"Random Wavelet Features for Graph Kernel Machines","created":"2026-02-17","cited_by_count":0,"area":null},{"id":"2603.04127","title":"Data-Aware Random Feature Kernel for Transformers","created":"2026-03-04","cited_by_count":0,"area":null},{"id":"2605.08171","title":"Communication Dynamics Neural Networks: FFT-Diagonalized Layers for Improved Hessian Conditioning at Reduced Parameter Count","created":"2026-05-04","cited_by_count":0,"area":null},{"id":"2606.11255","title":"Bernstein-Schur Kernels: Random Features by Sketched Modulation and Radial Randomization","created":"2026-06-08","cited_by_count":0,"area":null},{"id":"2607.22212","title":"Deep Convolutional Large-Margin $\\ell_p$-SVDD for Visual Anomaly Detection","created":"2026-07-24","cited_by_count":0,"area":null},{"id":"2607.23869","title":"A Coulomb Particle Model for Learning Kernel Attention in Transformers","created":"2026-07-26","cited_by_count":0,"area":null},{"id":"2608.04227","title":"Random features for Grassmannian kernel approximation with bounded rank-one projections","created":"2026-08-04","cited_by_count":0,"area":null},{"id":"2608.09307","title":"Linearized 2-Simplicial Attention","created":"2026-08-10","cited_by_count":0,"area":null},{"id":"2609.08136","title":"GPU-Enabled Large-Scale Optimization Using Randomized Linear Algebra","created":"2026-09-08","cited_by_count":0,"area":null},{"id":"2609.32320","title":"Superposed Inference for Hyperdimensional Computing","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.35038","title":"GUIDE-FBO: Guidance via Uncertainty Intervention and Distributional Exchange for Federated Bayesian Optimization","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.35177","title":"Subgroup Rank-1 Lattice for Practical High-dimensional Black-box Integral Approximation","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2610.13568","title":"Rationally Linearized MLPs","created":"2026-10-09","cited_by_count":0,"area":null},{"id":"2610.14751","title":"Random Fourier Features in Near-Linear Time","created":"2026-10-10","cited_by_count":0,"area":null}],"next_cursor":null}