{"list":"other","total":56,"rows":[{"id":"1611.01796","title":"Modular Multitask Reinforcement Learning with Policy Sketches","created":"2016-11-06","cited_by_count":203},{"id":"2007.07682","title":"FetchSGD: Communication-Efficient Federated Learning with Sketching","created":"2020-07-15","cited_by_count":179},{"id":"1405.5869","title":"Asymmetric LSH (ALSH) for Sublinear Time Maximum Inner Product Search (MIPS)","created":"2014-05-22","cited_by_count":109},{"id":"2302.13214","title":"Fast Attention Requires Bounded Entries","created":"2023-02-26","cited_by_count":102},{"id":"1810.07896","title":"Solving Linear Programs in the Current Matrix Multiplication Time","created":"2018-10-18","cited_by_count":100},{"id":"2310.05869","title":"HyperAttention: Long-context Attention in Near-Linear Time","created":"2023-10-09","cited_by_count":85},{"id":"2112.07628","title":"Training Multi-Layer Over-Parametrized Neural Network in Subquadratic Time","created":"2021-12-14","cited_by_count":62},{"id":"2302.02451","title":"KDEformer: Accelerating Transformers via Kernel Density Estimation","created":"2023-02-05","cited_by_count":58},{"id":"2004.04250","title":"An Improved Cutting Plane Method for Convex Optimization, Convex-Concave Games and its Applications","created":"2020-04-08","cited_by_count":57},{"id":"2010.05846","title":"A Refined Laser Method and Faster Matrix Multiplication","created":"2020-10-12","cited_by_count":56},{"id":"1905.04447","title":"Solving Empirical Risk Minimization in the Current Matrix Multiplication Time","created":"2019-05-11","cited_by_count":53},{"id":"2304.10411","title":"Attention Scheme Inspired Softmax Regression","created":"2023-04-20","cited_by_count":49},{"id":"1806.09823","title":"Approximate Nearest Neighbor Search in High Dimensions","created":"2018-06-26","cited_by_count":47},{"id":"1704.08246","title":"Relative Error Tensor Low Rank Approximation","created":"2017-04-26","cited_by_count":45},{"id":"1501.01062","title":"Optimal Data-Dependent Hashing for Approximate Near Neighbors","created":"2015-01-06","cited_by_count":44},{"id":"1611.03220","title":"Faster Kernel Ridge Regression Using Sketching and Preconditioning","created":"2016-11-10","cited_by_count":44},{"id":"2004.07470","title":"Faster Dynamic Matrix Inverse for Faster LPs","created":"2020-04-16","cited_by_count":44},{"id":"2303.15725","title":"Solving Regularized Exp, Cosh and Sinh Regression Problems","created":"2023-03-28","cited_by_count":44},{"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},{"id":"2211.06033","title":"A Faster Small Treewidth SDP Solver","created":"2022-11-11","cited_by_count":36},{"id":"2305.00660","title":"An Iterative Algorithm for Rescaled Hyperbolic Functions Regression","created":"2023-05-01","cited_by_count":35},{"id":"2108.09420","title":"Fast Sketching of Polynomial Kernels of Polynomial Degree","created":"2021-08-21","cited_by_count":33},{"id":"2106.07880","title":"Scaling Neural Tangent Kernels via Sketching and Random Features","created":"2021-06-15","cited_by_count":32},{"id":"2110.04622","title":"Does Preprocessing Help Training Over-parameterized Neural Networks?","created":"2021-10-09","cited_by_count":32},{"id":"2302.11068","title":"Low Rank Matrix Completion via Robust Alternating Minimization in Nearly Linear Time","created":"2023-02-21","cited_by_count":31},{"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},{"id":"1809.03054","title":"SEGA: Variance Reduction via Gradient Sketching","created":"2018-09-09","cited_by_count":29},{"id":"1909.13384","title":"Optimal Sketching for Kronecker Product Regression and Low Rank Approximation","created":"2019-09-29","cited_by_count":29},{"id":"2011.05365","title":"A Nearly-Linear Time Algorithm for Linear Programs with Small Treewidth: A Multiscale Representation of Robust Central Path","created":"2020-11-10","cited_by_count":29},{"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},{"id":"2211.14407","title":"Faster Algorithm for Structured John Ellipsoid Computation","created":"2022-11-26","cited_by_count":28},{"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},{"id":"1504.06729","title":"Optimal Principal Component Analysis in Distributed and Streaming Models","created":"2015-04-25","cited_by_count":24},{"id":"1905.11580","title":"A near-optimal algorithm for approximating the John Ellipsoid","created":"2019-05-28","cited_by_count":23},{"id":"1805.07674","title":"BourGAN: Generative Networks with Metric Embeddings","created":"2018-05-19","cited_by_count":22},{"id":"2204.03209","title":"Speeding Up Sparsification using Inner Product Search Data Structures","created":"2022-04-07","cited_by_count":22},{"id":"2208.05395","title":"A Sublinear Adversarial Training Algorithm","created":"2022-08-10","cited_by_count":22},{"id":"2210.11542","title":"Sketching Meets Differential Privacy: Fast Algorithm for Dynamic Kronecker Projection Maintenance","created":"2022-10-20","cited_by_count":22},{"id":"1806.06430","title":"Subspace Embedding and Linear Regression with Orlicz Norm","created":"2018-06-17","cited_by_count":19},{"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},{"id":"1410.5410","title":"Improved Asymmetric Locality Sensitive Hashing (ALSH) for Maximum Inner Product Search (MIPS)","created":"2014-10-20","cited_by_count":15},{"id":"2105.08285","title":"Sublinear Least-Squares Value Iteration via Locality Sensitive Hashing","created":"2021-05-18","cited_by_count":15},{"id":"2303.12298","title":"A General Algorithm for Solving Rank-one Matrix Sensing","created":"2023-03-22","cited_by_count":15},{"id":"2009.06106","title":"Space-Efficient Interior Point Method, with applications to Linear Programming and Maximum Weight Bipartite Matching","created":"2020-09-13","cited_by_count":14},{"id":"2212.11408","title":"Adaptive and Dynamic Multi-Resolution Hashing for Pairwise Summations","created":"2022-12-21","cited_by_count":14},{"id":"1601.07721","title":"Distributed Low Rank Approximation of Implicit Functions of a Matrix","created":"2016-01-28","cited_by_count":12},{"id":"1811.01442","title":"Towards a Zero-One Law for Column Subset Selection","created":"2018-11-04","cited_by_count":12},{"id":"2004.07986","title":"Average Case Column Subset Selection for Entrywise $\\ell_1$-Norm Loss","created":"2020-04-16","cited_by_count":12},{"id":"2310.12462","title":"Unmasking Transformers: A Theoretical Approach to Data Recovery via Attention Weights","created":"2023-10-19","cited_by_count":12},{"id":"1709.07093","title":"Near Optimal Sketching of Low-Rank Tensor Regression","created":"2017-09-20","cited_by_count":11},{"id":"2111.00664","title":"Optimal Sketching for Trace Estimation","created":"2021-11-01","cited_by_count":11},{"id":"2103.04031","title":"Accumulation of Sub-Sampling Matrices with Applications to Statistical Computation","created":"2021-03-06","cited_by_count":10},{"id":"2304.06594","title":"Solving Tensor Low Cycle Rank Approximation","created":"2023-04-13","cited_by_count":8},{"id":"2107.07657","title":"Streaming and Distributed Algorithms for Robust Column Subset Selection","created":"2021-07-16","cited_by_count":6},{"id":"2212.05176","title":"Adore: Differentially Oblivious Relational Database Operators","created":"2022-12-10","cited_by_count":6},{"id":"1810.06740","title":"An Illuminating Algorithm for the Light Bulb Problem","created":"2018-10-15","cited_by_count":3}],"next_cursor":null}