{"total":16,"rows":[{"id":"2209.04881","title":"On The Computational Complexity of Self-Attention","created":"2022-09-11","cited_by_count":139,"area":null},{"id":"2302.13214","title":"Fast Attention Requires Bounded Entries","created":"2023-02-26","cited_by_count":102,"area":null},{"id":"2207.01018","title":"Symbolic Regression is NP-hard","created":"2022-07-03","cited_by_count":71,"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":"2310.11685","title":"Why Softmax Attention Outperforms Linear Attention","created":"2023-10-18","cited_by_count":15,"area":null},{"id":"2106.03131","title":"The Fine-Grained Hardness of Sparse Linear Regression","created":"2021-06-06","cited_by_count":12,"area":null},{"id":"2102.08341","title":"Faster Kernel Matrix Algebra via Density Estimation","created":"2021-02-16","cited_by_count":8,"area":null},{"id":"2510.04008","title":"RACE Attention: A Strictly Linear-Time Attention Layer for Training on Outrageously Large Contexts","created":"2025-10-05","cited_by_count":5,"area":null},{"id":"2507.23539","title":"Improved Algorithms for Kernel Matrix-Vector Multiplication Under Sparsity Assumptions","created":"2025-07-31","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":"2311.01960","title":"Hardness of Low Rank Approximation of Entrywise Transformed Matrix Products","created":"2023-11-03","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":"2309.05795","title":"On the Fine-Grained Hardness of Inverting Generative Models","created":"2023-09-11","cited_by_count":1,"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":"2602.19017","title":"Why ReLU? A Bit-Model Dichotomy for Deep Network Training","created":"2026-02-22","cited_by_count":0,"area":null}],"next_cursor":null}