{"total":31,"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":"2303.16504","title":"An Over-parameterized Exponential Regression","created":"2023-03-29","cited_by_count":45,"area":null},{"id":"2306.04933","title":"InfoPrompt: Information-Theoretic Soft Prompt Tuning for Natural Language Understanding","created":"2023-06-08","cited_by_count":30,"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":"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":"2210.08371","title":"Sketching for First Order Method: Efficient Algorithm for Low-Bandwidth Channel and Vulnerability","created":"2022-10-15","cited_by_count":25,"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":"2208.04508","title":"Training Overparametrized Neural Networks in Sublinear Time","created":"2022-08-09","cited_by_count":22,"area":null},{"id":"2208.05395","title":"A Sublinear Adversarial Training Algorithm","created":"2022-08-10","cited_by_count":22,"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":"2111.15139","title":"Breaking the Linear Iteration Cost Barrier for Some Well-known Conditional Gradient Methods Using MaxIP Data-structures","created":"2021-11-30","cited_by_count":19,"area":null},{"id":"2410.10165","title":"HSR-Enhanced Sparse Attention Acceleration","created":"2024-10-14","cited_by_count":19,"area":null},{"id":"2307.08045","title":"Beyond Classical Attention: Quantum Attention for Scalable Computation","created":"2023-07-16","cited_by_count":18,"area":null},{"id":"2208.03635","title":"Federated Adversarial Learning: A Framework with Convergence Analysis","created":"2022-08-07","cited_by_count":17,"area":null},{"id":"2210.03961","title":"Dynamic Tensor Product Regression","created":"2022-10-08","cited_by_count":17,"area":null},{"id":"2206.12802","title":"Bounding the Width of Neural Networks via Coupled Initialization -- A Worst Case Analysis","created":"2022-06-26","cited_by_count":15,"area":null},{"id":"2303.12298","title":"A General Algorithm for Solving Rank-one Matrix Sensing","created":"2023-03-22","cited_by_count":15,"area":null},{"id":"2212.11408","title":"Adaptive and Dynamic Multi-Resolution Hashing for Pairwise Summations","created":"2022-12-21","cited_by_count":14,"area":null},{"id":"2407.13621","title":"Differential Privacy Mechanisms in Neural Tangent Kernel Regression","created":"2024-07-18","cited_by_count":14,"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":"2305.17482","title":"Federated Empirical Risk Minimization via Second-Order Method","created":"2023-05-27","cited_by_count":9,"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":"2310.11291","title":"An Automatic Learning Rate Schedule Algorithm for Achieving Faster Convergence and Steeper Descent","created":"2023-10-17","cited_by_count":9,"area":null},{"id":"2310.10224","title":"Generalizing Medical Image Representations via Quaternion Wavelet Networks","created":"2023-10-16","cited_by_count":6,"area":null},{"id":"2305.08001","title":"Structured and Fast Optimization: The Kronecker SGD Algorithm","created":"2023-05-13","cited_by_count":5,"area":null},{"id":"2301.00335","title":"Pruning Before Training May Improve Generalization, Provably","created":"2023-01-01","cited_by_count":3,"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":"2301.00327","title":"Neural Networks with Sparse Activation Induced by Large Bias: Tighter Analysis with Bias-Generalized NTK","created":"2023-01-01","cited_by_count":2,"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}],"next_cursor":null}