{"total":57,"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":"2304.10411","title":"Attention Scheme Inspired Softmax Regression","created":"2023-04-20","cited_by_count":49,"area":null},{"id":"2303.15725","title":"Solving Regularized Exp, Cosh and Sinh Regression Problems","created":"2023-03-28","cited_by_count":44,"area":null},{"id":"2304.04397","title":"Randomized and Deterministic Attention Sparsification Algorithms for Over-parameterized Feature Dimension","created":"2023-04-10","cited_by_count":37,"area":null},{"id":"2305.00660","title":"An Iterative Algorithm for Rescaled Hyperbolic Functions Regression","created":"2023-05-01","cited_by_count":35,"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":"2110.04622","title":"Does Preprocessing Help Training Over-parameterized Neural Networks?","created":"2021-10-09","cited_by_count":32,"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":"2306.02295","title":"A Mathematical Abstraction for Balancing the Trade-off Between Creativity and Reality in Large Language Models","created":"2023-06-04","cited_by_count":29,"area":null},{"id":"2106.09481","title":"Stochastic Bias-Reduced Gradient Methods","created":"2021-06-17","cited_by_count":25,"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":"2208.04508","title":"Training Overparametrized Neural Networks in Sublinear Time","created":"2022-08-09","cited_by_count":22,"area":null},{"id":"2408.12151","title":"A Tighter Complexity Analysis of SparseGPT","created":"2024-08-22","cited_by_count":19,"area":null},{"id":"2210.03961","title":"Dynamic Tensor Product Regression","created":"2022-10-08","cited_by_count":17,"area":null},{"id":"2301.00457","title":"ReSQueing Parallel and Private Stochastic Convex Optimization","created":"2023-01-01","cited_by_count":17,"area":null},{"id":"2105.08285","title":"Sublinear Least-Squares Value Iteration via Locality Sensitive Hashing","created":"2021-05-18","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":"2203.15260","title":"Efficient Convex Optimization Requires Superlinear Memory","created":"2022-03-29","cited_by_count":14,"area":null},{"id":"2103.00564","title":"An Introduction to Johnson-Lindenstrauss Transforms","created":"2021-02-28","cited_by_count":11,"area":null},{"id":"2305.08367","title":"Toward Highly Efficient and Private Submodular Maximization via Matrix-Based Acceleration","created":"2023-05-15","cited_by_count":11,"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":"2306.06778","title":"Approximation Algorithms for Fair Range Clustering","created":"2023-06-11","cited_by_count":10,"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":"2304.06594","title":"Solving Tensor Low Cycle Rank Approximation","created":"2023-04-13","cited_by_count":8,"area":null},{"id":"2311.05436","title":"Fair Wasserstein Coresets","created":"2023-11-09","cited_by_count":8,"area":null},{"id":"2305.08353","title":"Fast and Efficient Matching Algorithm with Deadline Instances","created":"2023-05-15","cited_by_count":7,"area":null},{"id":"2302.04963","title":"Quadratic Memory is Necessary for Optimal Query Complexity in Convex Optimization: Center-of-Mass is Pareto-Optimal","created":"2023-02-09","cited_by_count":5,"area":null},{"id":"2311.00109","title":"FairWASP: Fast and Optimal Fair Wasserstein Pre-processing","created":"2023-10-31","cited_by_count":5,"area":null},{"id":"2107.05187","title":"Polynomial Time Reinforcement Learning in Factored State MDPs with Linear Value Functions","created":"2021-07-12","cited_by_count":4,"area":null},{"id":"2211.15118","title":"A Faster $k$-means++ Algorithm","created":"2022-11-28","cited_by_count":4,"area":null},{"id":"2306.02212","title":"Accelerated Quasi-Newton Proximal Extragradient: Faster Rate for Smooth Convex Optimization","created":"2023-06-03","cited_by_count":4,"area":null},{"id":"2306.12534","title":"Memory-Query Tradeoffs for Randomized Convex Optimization","created":"2023-06-21","cited_by_count":4,"area":null},{"id":"2502.21240","title":"The Structural Complexity of Matrix-Vector Multiplication","created":"2025-02-28","cited_by_count":4,"area":null},{"id":"2103.03868","title":"Decomposable Submodular Function Minimization via Maximum Flow","created":"2021-03-05","cited_by_count":3,"area":null},{"id":"2306.10096","title":"Memory-Constrained Algorithms for Convex Optimization via Recursive Cutting-Planes","created":"2023-06-16","cited_by_count":3,"area":null},{"id":"2406.07373","title":"Closing the Computational-Query Depth Gap in Parallel Stochastic Convex Optimization","created":"2024-06-11","cited_by_count":3,"area":null},{"id":"2502.16912","title":"When Can We Solve the Weighted Low Rank Approximation Problem in Truly Subquadratic Time?","created":"2025-02-24","cited_by_count":3,"area":null},{"id":"2510.02983","title":"Oracle-based Uniform Sampling from Convex Bodies","created":"2025-10-03","cited_by_count":3,"area":null},{"id":"2512.23190","title":"A Simple, Optimal and Efficient Algorithm for Online Exp-Concave Optimization","created":"2025-12-29","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":"2103.01061","title":"A Hybrid Quantum-Classical Hamiltonian Learning Algorithm","created":"2021-03-01","cited_by_count":1,"area":null},{"id":"2404.06720","title":"Gradient Descent is Pareto-Optimal in the Oracle Complexity and Memory Tradeoff for Feasibility Problems","created":"2024-04-10","cited_by_count":1,"area":null},{"id":"2405.06003","title":"Binary Hypothesis Testing for Softmax Models and Leverage Score Models","created":"2024-05-09","cited_by_count":1,"area":null},{"id":"2405.14090","title":"Solving 0-1 Integer Programs with Unknown Knapsack Constraints Using Membership Oracles","created":"2024-05-23","cited_by_count":1,"area":null},{"id":"2410.02145","title":"Active Learning of Deep Neural Networks via Gradient-Free Cutting Planes","created":"2024-10-03","cited_by_count":1,"area":null},{"id":"2501.03222","title":"Characterizing the Accuracy-Communication-Privacy Trade-off in Distributed Stochastic Convex Optimization","created":"2025-01-06","cited_by_count":1,"area":null},{"id":"2506.20141","title":"Accept More, Reject Less: Reducing up to 19% Unnecessary Desk-Rejections over 11 Years of ICLR Data","created":"2025-06-25","cited_by_count":1,"area":null},{"id":"2608.08463","title":"Halpern Iteration Achieves $\\tilde{\\mathcal{O}}(\\epsilon^{-1/p})$ $p$th-Order Oracle Complexity for Monotone Variational Inequalities","created":"2026-08-09","cited_by_count":1,"area":null},{"id":"2208.03811","title":"Decomposable Non-Smooth Convex Optimization with Nearly-Linear Gradient Oracle Complexity","created":"2022-08-07","cited_by_count":0,"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":"2503.17308","title":"On Quantum Perceptron Learning via Quantum Search","created":"2025-03-21","cited_by_count":0,"area":null},{"id":"2607.04062","title":"Fast, Parallel, Query-Efficient Binary Classification","created":"2026-07-05","cited_by_count":0,"area":null},{"id":"2607.24827","title":"Stronger Memory-Query Tradeoffs for Convex Optimization: The Limitations of Subquadratic Memory","created":"2026-07-21","cited_by_count":0,"area":null},{"id":"2608.12302","title":"A Framework for Designing Reward Functions: From Objectives to Features to Human-Aligned Reward Functions","created":"2026-08-12","cited_by_count":0,"area":null},{"id":"2609.14065","title":"Stabilizing Performative Feedback Loops with Minimal Model Deployments","created":"2026-09-12","cited_by_count":0,"area":null},{"id":"2609.23557","title":"Optimal High-Order Methods for Solving Monotone Variational Inequalities","created":"2026-09-20","cited_by_count":0,"area":null}],"next_cursor":null}