{"total":51,"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":"2110.04622","title":"Does Preprocessing Help Training Over-parameterized Neural Networks?","created":"2021-10-09","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":"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":"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":"2208.05395","title":"A Sublinear Adversarial Training Algorithm","created":"2022-08-10","cited_by_count":22,"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":"2408.12151","title":"A Tighter Complexity Analysis of SparseGPT","created":"2024-08-22","cited_by_count":19,"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":"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":"2312.08893","title":"Solving Dense Linear Systems Faster Than via Preconditioning","created":"2023-12-14","cited_by_count":12,"area":null},{"id":"2311.10680","title":"Optimal Embedding Dimension for Sparse Subspace Embeddings","created":"2023-11-17","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":"2402.07240","title":"Oja's Algorithm for Streaming Sparse PCA","created":"2024-02-11","cited_by_count":9,"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":"2201.08226","title":"Sketch-and-Lift: Scalable Subsampled Semidefinite Program for $K$-means Clustering","created":"2022-01-20","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":"2505.04514","title":"Quantum thermodynamics and semi-definite optimization","created":"2025-05-07","cited_by_count":5,"area":null},{"id":"2107.08090","title":"Near-Optimal Algorithms for Linear Algebra in the Current Matrix Multiplication Time","created":"2021-07-16","cited_by_count":4,"area":null},{"id":"2308.03661","title":"Matrix Completion in Almost-Verification Time","created":"2023-08-07","cited_by_count":4,"area":null},{"id":"2405.05865","title":"Faster Linear Systems and Matrix Norm Approximation via Multi-level Sketched Preconditioning","created":"2024-05-09","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":"2505.13564","title":"Online Decision-Focused Learning","created":"2025-05-19","cited_by_count":4,"area":null},{"id":"2511.21008","title":"Estimating Ising Models in Total Variation Distance","created":"2025-11-26","cited_by_count":3,"area":null},{"id":"2108.04729","title":"Spectral Robustness for Correlation Clustering Reconstruction in Semi-Adversarial Models","created":"2021-08-10","cited_by_count":2,"area":null},{"id":"2111.12550","title":"A Worker-Task Specialization Model for Crowdsourcing: Efficient Inference and Fundamental Limits","created":"2021-11-19","cited_by_count":2,"area":null},{"id":"2208.12227","title":"Community Detection in the Hypergraph SBM: Exact Recovery Given the Similarity Matrix","created":"2022-08-23","cited_by_count":2,"area":null},{"id":"2209.15097","title":"Likelihood Adjusted Semidefinite Programs for Clustering Heterogeneous Data","created":"2022-09-29","cited_by_count":2,"area":null},{"id":"2306.06845","title":"Information-Theoretic Limits and Strong Consistency on Binary Non-uniform Hypergraph Stochastic Block Models","created":"2023-06-12","cited_by_count":2,"area":null},{"id":"2401.13779","title":"Faster Convergence with Less Communication: Broadcast-Based Subgraph Sampling for Decentralized Learning over Wireless Networks","created":"2024-01-24","cited_by_count":2,"area":null},{"id":"2408.04705","title":"Overlay-based Decentralized Federated Learning in Bandwidth-limited Networks","created":"2024-08-08","cited_by_count":2,"area":null},{"id":"2508.09103","title":"Constrained free energy minimization for the design of thermal states and stabilizer thermodynamic systems","created":"2025-08-12","cited_by_count":2,"area":null},{"id":"2111.07834","title":"Conditional Linear Regression for Heterogeneous Covariances","created":"2021-11-15","cited_by_count":1,"area":null},{"id":"2112.13832","title":"Faster Algorithms and Constant Lower Bounds for the Worst-Case Expected Error","created":"2021-12-27","cited_by_count":1,"area":null},{"id":"2310.09687","title":"When Collaborative Filtering is not Collaborative: Unfairness of PCA for Recommendations","created":"2023-10-15","cited_by_count":1,"area":null},{"id":"2401.03083","title":"Energy-efficient Decentralized Learning via Graph Sparsification","created":"2024-01-05","cited_by_count":1,"area":null},{"id":"2401.07606","title":"RedEx: Beyond Fixed Representation Methods via Convex Optimization","created":"2024-01-15","cited_by_count":1,"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":"2403.04726","title":"A Sub-Quadratic Time Algorithm for Robust Sparse Mean Estimation","created":"2024-03-07","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":"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":"2604.27786","title":"On the Expressive Power of GNNs to Solve Linear SDPs","created":"2026-04-30","cited_by_count":1,"area":null},{"id":"2605.24803","title":"Active Learning for Stochastic Contextual Linear Bandits","created":"2026-05-24","cited_by_count":1,"area":null},{"id":"2306.16516","title":"Dimension-Independent Kernel {\\epsilon}-Covers","created":"2023-06-28","cited_by_count":0,"area":null},{"id":"2412.13372","title":"Sum-of-Squares Programming for Ma-Trudinger-Wang Regularity of Optimal Transport Maps","created":"2024-12-17","cited_by_count":0,"area":null},{"id":"2607.09909","title":"Learning Partition Trees for Nearest Neighbor Search","created":"2026-07-10","cited_by_count":0,"area":null}],"next_cursor":null}