{"list":"other","total":65,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2407.02490","title":"MInference 1.0: Accelerating Pre-filling for Long-Context LLMs via Dynamic Sparse Attention","created":"2024-07-02","cited_by_count":383},{"id":"2207.00112","title":"Language model compression with weighted low-rank factorization","created":"2022-06-30","cited_by_count":195},{"id":"2412.05496","title":"Flex Attention: A Programming Model for Generating Optimized Attention Kernels","created":"2024-12-07","cited_by_count":185},{"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":"2112.07628","title":"Training Multi-Layer Over-Parametrized Neural Network in Subquadratic Time","created":"2021-12-14","cited_by_count":62},{"id":"2006.11648","title":"Training (Overparametrized) Neural Networks in Near-Linear Time","created":"2020-06-20","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":"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":"2405.19592","title":"Why Larger Language Models Do In-context Learning Differently?","created":"2024-05-30","cited_by_count":45},{"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":"1910.11957","title":"A Deterministic Linear Program Solver in Current Matrix Multiplication Time","created":"2019-10-25","cited_by_count":42},{"id":"1509.03917","title":"Dropping Convexity for Faster Semi-definite Optimization","created":"2015-09-14","cited_by_count":40},{"id":"2407.01079","title":"On Statistical Rates and Provably Efficient Criteria of Latent Diffusion Transformers (DiTs)","created":"2024-07-01","cited_by_count":40},{"id":"2407.15720","title":"Do Large Language Models Have Compositional Ability? An Investigation into Limitations and Scalability","created":"2024-07-22","cited_by_count":40},{"id":"2409.17422","title":"Discovering the Gems in Early Layers: Accelerating Long-Context LLMs with 1000x Input Token Reduction","created":"2024-09-25","cited_by_count":39},{"id":"2304.04397","title":"Randomized and Deterministic Attention Sparsification Algorithms for Over-parameterized Feature Dimension","created":"2023-04-10","cited_by_count":37},{"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":"2405.05219","title":"Conv-Basis: A New Paradigm for Efficient Attention Inference and Gradient Computation in Transformers","created":"2024-05-08","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":"2406.03136","title":"Computational Limits of Low-Rank Adaptation (LoRA) Fine-Tuning for Transformer Models","created":"2024-06-05","cited_by_count":31},{"id":"2405.16411","title":"Training Tensor Attention Efficiently: From Cubic to Almost Linear Time","created":"2024-05-26","cited_by_count":30},{"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},{"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":"1905.11580","title":"A near-optimal algorithm for approximating the John Ellipsoid","created":"2019-05-28","cited_by_count":23},{"id":"2204.03209","title":"Speeding Up Sparsification using Inner Product Search Data Structures","created":"2022-04-07","cited_by_count":22},{"id":"2208.04508","title":"Training Overparametrized Neural Networks in Sublinear Time","created":"2022-08-09","cited_by_count":22},{"id":"2208.05395","title":"A Sublinear Adversarial Training Algorithm","created":"2022-08-10","cited_by_count":22},{"id":"2210.12468","title":"Discrepancy Minimization in Input-Sparsity Time","created":"2022-10-22","cited_by_count":22},{"id":"2402.09469","title":"Fourier Circuits in Neural Networks and Transformers: A Case Study of Modular Arithmetic with Multiple Inputs","created":"2024-02-12","cited_by_count":22},{"id":"2408.13233","title":"Multi-Layer Transformers Gradient Can be Approximated in Almost Linear Time","created":"2024-08-23","cited_by_count":22},{"id":"2410.11268","title":"Bypassing the Exponential Dependency: Looped Transformers Efficiently Learn In-context by Multi-step Gradient Descent","created":"2024-10-15","cited_by_count":22},{"id":"2411.16525","title":"Fundamental Limits of Prompt Tuning Transformers: Universality, Capacity and Efficiency","created":"2024-11-25","cited_by_count":22},{"id":"2411.17522","title":"On Statistical Rates of Conditional Diffusion Transformers: Approximation, Estimation and Minimax Optimality","created":"2024-11-26","cited_by_count":22},{"id":"1602.02262","title":"Recovery guarantee of weighted low-rank approximation via alternating minimization","created":"2016-02-06","cited_by_count":20},{"id":"2410.11261","title":"Beyond Linear Approximations: A Novel Pruning Approach for Attention Matrix","created":"2024-10-15","cited_by_count":20},{"id":"2408.12151","title":"A Tighter Complexity Analysis of SparseGPT","created":"2024-08-22","cited_by_count":19},{"id":"2410.10165","title":"HSR-Enhanced Sparse Attention Acceleration","created":"2024-10-14","cited_by_count":19},{"id":"2303.12298","title":"A General Algorithm for Solving Rank-one Matrix Sensing","created":"2023-03-22","cited_by_count":15},{"id":"2405.03251","title":"Exploring the Frontiers of Softmax: Provable Optimization, Applications in Diffusion Model, and Beyond","created":"2024-05-06","cited_by_count":15},{"id":"2211.09718","title":"Numerical Optimizations for Weighted Low-rank Estimation on Language Model","created":"2022-11-02","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":"2501.04377","title":"On Computational Limits and Provably Efficient Criteria of Visual Autoregressive Models: A Fine-Grained Complexity Analysis","created":"2025-01-08","cited_by_count":14},{"id":"2412.17316","title":"RoPE Attention Can Be Trained in Almost Linear Time","created":"2024-12-23","cited_by_count":13},{"id":"2303.07527","title":"Domain Generalization via Nuclear Norm Regularization","created":"2023-03-13","cited_by_count":12},{"id":"2304.03426","title":"Convex Minimization with Integer Minima in $\\widetilde O(n^4)$ Time","created":"2023-04-07","cited_by_count":12},{"id":"1911.06958","title":"Regularized Weighted Low Rank Approximation","created":"2019-11-16","cited_by_count":10},{"id":"2109.05736","title":"Effective Tensor Completion via Element-wise Weighted Low-rank Tensor Train with Overlapping Ket Augmentation","created":"2021-09-13","cited_by_count":8},{"id":"1901.10371","title":"On the Effect of Low-Rank Weights on Adversarial Robustness of Neural Networks","created":"2019-01-29","cited_by_count":7},{"id":"2110.10279","title":"Factorization Approach for Low-complexity Matrix Completion Problems: Exponential Number of Spurious Solutions and Failure of Gradient Methods","created":"2021-10-19","cited_by_count":6},{"id":"1409.1534","title":"Algorithms in Real Algebraic Geometry: A Survey","created":"2014-09-04","cited_by_count":5},{"id":"1410.3886","title":"Tighter Low-rank Approximation via Sampling the Leveraged Element","created":"2014-10-14","cited_by_count":3},{"id":"2204.02364","title":"A New Complexity Metric for Nonconvex Rank-one Generalized Matrix Completion","created":"2022-04-05","cited_by_count":3},{"id":"1707.01753","title":"Weighted Low Rank Approximation for Background Estimation Problems","created":"2017-07-04","cited_by_count":2},{"id":"1804.06252","title":"Weighted Low-Rank Approximation of Matrices and Background Modeling","created":"2018-04-15","cited_by_count":2},{"id":"2109.11057","title":"Weighted Low-Rank Matrix Approximation: Acceleration and Applications","created":"2021-09-22","cited_by_count":2},{"id":"1703.06303","title":"A Fast Algorithm for a Weighted Low Rank Approximation","created":"2017-03-18","cited_by_count":1},{"id":"2104.12308","title":"Auto-weighted low-rank representation for clustering","created":"2021-04-26","cited_by_count":1},{"id":"2406.02431","title":"Reweighted Solutions for Weighted Low Rank Approximation","created":"2024-06-04","cited_by_count":1}],"next_cursor":null}