{"list":"other","total":53,"rows":[{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"1806.07572","title":"Neural Tangent Kernel: Convergence and Generalization in Neural Networks","created":"2018-06-20","cited_by_count":2621},{"id":"1503.05671","title":"Optimizing Neural Networks with Kronecker-factored Approximate Curvature","created":"2015-03-19","cited_by_count":796},{"id":"1811.03962","title":"A Convergence Theory for Deep Learning via Over-Parameterization","created":"2018-11-09","cited_by_count":787},{"id":"1902.06720","title":"Wide Neural Networks of Any Depth Evolve as Linear Models Under Gradient Descent","created":"2019-02-18","cited_by_count":738},{"id":"1810.02054","title":"Gradient Descent Provably Optimizes Over-parameterized Neural Networks","created":"2018-10-04","cited_by_count":659},{"id":"1811.03804","title":"Gradient Descent Finds Global Minima of Deep Neural Networks","created":"2018-11-09","cited_by_count":574},{"id":"1901.08584","title":"Fine-Grained Analysis of Optimization and Generalization for Overparameterized Two-Layer Neural Networks","created":"2019-01-24","cited_by_count":566},{"id":"1411.4357","title":"Sketching as a Tool for Numerical Linear Algebra","created":"2014-11-17","cited_by_count":288},{"id":"1808.01204","title":"Learning Overparameterized Neural Networks via Stochastic Gradient Descent on Structured Data","created":"2018-08-03","cited_by_count":261},{"id":"2003.00307","title":"Loss landscapes and optimization in over-parameterized non-linear systems and neural networks","created":"2020-02-29","cited_by_count":233},{"id":"1905.13210","title":"Generalization Bounds of Stochastic Gradient Descent for Wide and Deep Neural Networks","created":"2019-05-30","cited_by_count":222},{"id":"2006.00719","title":"ADAHESSIAN: An Adaptive Second Order Optimizer for Machine Learning","created":"2020-06-01","cited_by_count":202},{"id":"1902.04674","title":"Towards moderate overparameterization: global convergence guarantees for training shallow neural networks","created":"2019-02-12","cited_by_count":176},{"id":"1706.03662","title":"Practical Gauss-Newton Optimisation for Deep Learning","created":"2017-06-12","cited_by_count":142},{"id":"2010.01092","title":"On the linearity of large non-linear models: when and why the tangent kernel is constant","created":"2020-10-02","cited_by_count":129},{"id":"1906.04688","title":"An Improved Analysis of Training Over-parameterized Deep Neural Networks","created":"2019-06-11","cited_by_count":121},{"id":"1810.07896","title":"Solving Linear Programs in the Current Matrix Multiplication Time","created":"2018-10-18","cited_by_count":100},{"id":"1911.12360","title":"How Much Over-parameterization Is Sufficient to Learn Deep ReLU Networks?","created":"2019-11-27","cited_by_count":84},{"id":"1810.12065","title":"On the Convergence Rate of Training Recurrent Neural Networks","created":"2018-10-29","cited_by_count":82},{"id":"1905.10961","title":"Fast Convergence of Natural Gradient Descent for Overparameterized Neural Networks","created":"2019-05-27","cited_by_count":76},{"id":"1505.02250","title":"Newton Sketch: A Linear-time Optimization Algorithm with Linear-Quadratic Convergence","created":"2015-05-09","cited_by_count":72},{"id":"1906.03593","title":"Quadratic Suffices for Over-parametrization via Matrix Chernoff Bound","created":"2019-06-09","cited_by_count":59},{"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":"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":"2009.10217","title":"A Faster Interior Point Method for Semidefinite Programming","created":"2020-09-21","cited_by_count":53},{"id":"1508.04874","title":"A Faster Cutting Plane Method and its Implications for Combinatorial and Convex Optimization","created":"2015-08-20","cited_by_count":50},{"id":"1903.03129","title":"SLIDE : In Defense of Smart Algorithms over Hardware Acceleration for Large-Scale Deep Learning Systems","created":"2019-03-07","cited_by_count":46},{"id":"1704.08246","title":"Relative Error Tensor Low Rank Approximation","created":"2017-04-26","cited_by_count":45},{"id":"2004.07470","title":"Faster Dynamic Matrix Inverse for Faster LPs","created":"2020-04-16","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":"1905.11675","title":"Gram-Gauss-Newton Method: Learning Overparameterized Neural Networks for Regression Problems","created":"2019-05-28","cited_by_count":40},{"id":"2101.08208","title":"Solving SDP Faster: A Robust IPM Framework and Efficient Implementation","created":"2021-01-20","cited_by_count":33},{"id":"2108.09420","title":"Fast Sketching of Polynomial Kernels of Polynomial Degree","created":"2021-08-21","cited_by_count":33},{"id":"2110.04622","title":"Does Preprocessing Help Training Over-parameterized Neural Networks?","created":"2021-10-09","cited_by_count":32},{"id":"1712.09473","title":"Sketching for Kronecker Product Regression and P-splines","created":"2017-12-27","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":"2009.09829","title":"Generalized Leverage Score Sampling for Neural Networks","created":"2020-09-21","cited_by_count":26},{"id":"1504.06729","title":"Optimal Principal Component Analysis in Distributed and Streaming Models","created":"2015-04-25","cited_by_count":24},{"id":"2107.07480","title":"Newton-LESS: Sparsification without Trade-offs for the Sketched Newton Update","created":"2021-07-15","cited_by_count":23},{"id":"2002.02304","title":"Solving Tall Dense Linear Programs in Nearly Linear Time","created":"2020-02-06","cited_by_count":21},{"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":"1708.05622","title":"Improved Rectangular Matrix Multiplication using Powers of the Coppersmith-Winograd Tensor","created":"2017-08-18","cited_by_count":13},{"id":"2105.05001","title":"FL-NTK: A Neural Tangent Kernel-based Framework for Federated Learning Convergence Analysis","created":"2021-05-11","cited_by_count":13},{"id":"2007.03927","title":"Near Input Sparsity Time Kernel Embeddings via Adaptive Sampling","created":"2020-07-08","cited_by_count":12},{"id":"1910.01788","title":"Efficient Symmetric Norm Regression via Linear Sketching","created":"2019-10-04","cited_by_count":7},{"id":"2101.07233","title":"Fully Dynamic Electrical Flows: Sparse Maxflow Faster Than Goldberg-Rao","created":"2021-01-18","cited_by_count":6},{"id":"2110.15533","title":"Improved Sliding Window Algorithms for Clustering and Coverage via Bucketing-Based Sketches","created":"2021-10-29","cited_by_count":5},{"id":"2112.00722","title":"Faster Maxflow via Improved Dynamic Spectral Vertex Sparsifiers","created":"2021-12-01","cited_by_count":3},{"id":"2111.10368","title":"Faster Sparse Minimum Cost Flow by Electrical Flow Localization","created":"2021-11-19","cited_by_count":2}],"next_cursor":null}