{"total":21,"rows":[{"id":"2302.13214","title":"Fast Attention Requires Bounded Entries","created":"2023-02-26","cited_by_count":102,"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":"2108.09420","title":"Fast Sketching of Polynomial Kernels of Polynomial Degree","created":"2021-08-21","cited_by_count":33,"area":null},{"id":"2406.03136","title":"Computational Limits of Low-Rank Adaptation (LoRA) Fine-Tuning for Transformer Models","created":"2024-06-05","cited_by_count":31,"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":"2405.16411","title":"Training Tensor Attention Efficiently: From Cubic to Almost Linear Time","created":"2024-05-26","cited_by_count":30,"area":null},{"id":"2211.14227","title":"Bypass Exponential Time Preprocessing: Fast Neural Network Training via Weight-Data Correlation Preprocessing","created":"2022-11-25","cited_by_count":29,"area":null},{"id":"2310.11685","title":"Why Softmax Attention Outperforms Linear Attention","created":"2023-10-18","cited_by_count":15,"area":null},{"id":"2307.01877","title":"Fast Private Kernel Density Estimation via Locality Sensitive Quantization","created":"2023-07-04","cited_by_count":9,"area":null},{"id":"2307.06877","title":"The complexity of non-stationary reinforcement learning","created":"2023-07-13","cited_by_count":7,"area":null},{"id":"2208.03915","title":"Dynamic Maintenance of Kernel Density Estimation Data Structure: From Practice to Theory","created":"2022-08-08","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":"2502.21240","title":"The Structural Complexity of Matrix-Vector Multiplication","created":"2025-02-28","cited_by_count":4,"area":null},{"id":"2201.00228","title":"The Complexity of Dynamic Least-Squares Regression","created":"2022-01-01","cited_by_count":3,"area":null},{"id":"2310.13870","title":"Fast Approximation of Similarity Graphs with Kernel Density Estimation","created":"2023-10-21","cited_by_count":3,"area":null},{"id":"2311.01960","title":"Hardness of Low Rank Approximation of Entrywise Transformed Matrix Products","created":"2023-11-03","cited_by_count":3,"area":null},{"id":"2409.01688","title":"Differentially Private Kernel Density Estimation","created":"2024-09-03","cited_by_count":3,"area":null},{"id":"2212.00642","title":"Sub-quadratic Algorithms for Kernel Matrices via Kernel Density Estimation","created":"2022-12-01","cited_by_count":2,"area":null},{"id":"2510.02540","title":"Even Faster Kernel Matrix Linear Algebra via Density Estimation","created":"2025-10-02","cited_by_count":1,"area":null},{"id":"2304.03452","title":"Graph Enabled Cross-Domain Knowledge Transfer","created":"2023-04-07","cited_by_count":0,"area":null},{"id":"2305.06541","title":"Spectral Clustering on Large Datasets: When Does it Work? Theory from Continuous Clustering and Density Cheeger-Buser","created":"2023-05-11","cited_by_count":0,"area":null}],"next_cursor":null}