{"total":33,"rows":[{"id":"2112.07628","title":"Training Multi-Layer Over-Parametrized Neural Network in Subquadratic Time","created":"2021-12-14","cited_by_count":62,"area":null},{"id":"2310.04064","title":"How to Capture Higher-order Correlations? Generalizing Matrix Softmax Attention to Kronecker Computation","created":"2023-10-06","cited_by_count":44,"area":null},{"id":"2310.01655","title":"PolySketchFormer: Fast Transformers via Sketching Polynomial Kernels","created":"2023-10-02","cited_by_count":36,"area":null},{"id":"2307.02419","title":"In-Context Learning for Attention Scheme: from Single Softmax Regression to Multiple Softmax Regression via a Tensor Trick","created":"2023-07-05","cited_by_count":32,"area":null},{"id":"2302.11068","title":"Low Rank Matrix Completion via Robust Alternating Minimization in Nearly Linear Time","created":"2023-02-21","cited_by_count":31,"area":null},{"id":"2309.07418","title":"A Fast Optimization View: Reformulating Single Layer Attention in LLM Based on Tensor and SVM Trick, and Solving It in Matrix Multiplication Time","created":"2023-09-14","cited_by_count":30,"area":null},{"id":"2402.04497","title":"The Fine-Grained Complexity of Gradient Computation for Training Large Language Models","created":"2024-02-07","cited_by_count":30,"area":null},{"id":"2308.10502","title":"GradientCoin: A Peer-to-Peer Decentralized Large Language Models","created":"2023-08-21","cited_by_count":23,"area":null},{"id":"2308.14304","title":"Solving Attention Kernel Regression Problem via Pre-conditioner","created":"2023-08-28","cited_by_count":20,"area":null},{"id":"2210.03961","title":"Dynamic Tensor Product Regression","created":"2022-10-08","cited_by_count":17,"area":null},{"id":"2302.00248","title":"A Nearly-Optimal Bound for Fast Regression with $\\ell_\\infty$ Guarantee","created":"2023-02-01","cited_by_count":14,"area":null},{"id":"2201.08712","title":"Improved Random Features for Dot Product Kernels","created":"2022-01-21","cited_by_count":12,"area":null},{"id":"2307.06565","title":"Efficient SGD Neural Network Training via Sublinear Activated Neuron Identification","created":"2023-07-13","cited_by_count":11,"area":null},{"id":"2303.06210","title":"A Theoretical Analysis Of Nearest Neighbor Search On Approximate Near Neighbor Graph","created":"2023-03-10","cited_by_count":10,"area":null},{"id":"2306.04169","title":"Efficient Alternating Minimization with Applications to Weighted Low Rank Approximation","created":"2023-06-07","cited_by_count":9,"area":null},{"id":"2304.06594","title":"Solving Tensor Low Cycle Rank Approximation","created":"2023-04-13","cited_by_count":8,"area":null},{"id":"2204.10376","title":"Differentially Private Learning with Margin Guarantees","created":"2022-04-21","cited_by_count":7,"area":null},{"id":"2208.03367","title":"Sublinear Time Algorithm for Online Weighted Bipartite Matching","created":"2022-08-05","cited_by_count":7,"area":null},{"id":"2408.06395","title":"Fast John Ellipsoid Computation with Differential Privacy Optimization","created":"2024-08-12","cited_by_count":7,"area":null},{"id":"2505.16284","title":"Only Large Weights (And Not Skip Connections) Can Prevent the Perils of Rank Collapse","created":"2025-05-22","cited_by_count":7,"area":null},{"id":"2202.03474","title":"Random Gegenbauer Features for Scalable Kernel Methods","created":"2022-02-07","cited_by_count":6,"area":null},{"id":"2202.04515","title":"Leverage Score Sampling for Tensor Product Matrices in Input Sparsity Time","created":"2022-02-09","cited_by_count":6,"area":null},{"id":"2303.04555","title":"Streaming Kernel PCA Algorithm With Small Space","created":"2023-03-08","cited_by_count":5,"area":null},{"id":"2202.02031","title":"Complex-to-Real Sketches for Tensor Products with Applications to the Polynomial Kernel","created":"2022-02-04","cited_by_count":4,"area":null},{"id":"2112.02446","title":"Fast Graph Neural Tangent Kernel via Kronecker Sketching","created":"2021-12-04","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":"2410.05700","title":"Log-concave Sampling from a Convex Body with a Barrier: a Robust and Unified Dikin Walk","created":"2024-10-08","cited_by_count":2,"area":null},{"id":"2402.07027","title":"Quantum Speedup for Spectral Approximation of Kronecker Products","created":"2024-02-10","cited_by_count":1,"area":null},{"id":"2507.10701","title":"Kernel Learning for Mean-Variance Trading Strategies","created":"2025-07-14","cited_by_count":1,"area":null},{"id":"2510.03678","title":"Towards Sampling Data Structures for Tensor Products in Turnstile Streams","created":"2025-10-04","cited_by_count":1,"area":null},{"id":"2309.01030","title":"Online Adaptive Mahalanobis Distance Estimation","created":"2023-09-02","cited_by_count":0,"area":null},{"id":"2311.11429","title":"Fast Heavy Inner Product Identification Between Weights and Inputs in Neural Network Training","created":"2023-11-19","cited_by_count":0,"area":null},{"id":"2512.12238","title":"Semantic Distance Measurement based on Multi-Kernel Gaussian Processes","created":"2025-12-13","cited_by_count":0,"area":null}],"next_cursor":null}