{"list":"other","total":64,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"1409.4842","title":"Going Deeper with Convolutions","created":"2014-09-17","cited_by_count":4241},{"id":"1806.07572","title":"Neural Tangent Kernel: Convergence and Generalization in Neural Networks","created":"2018-06-20","cited_by_count":2621},{"id":"1811.03962","title":"A Convergence Theory for Deep Learning via Over-Parameterization","created":"2018-11-09","cited_by_count":787},{"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":"1808.01204","title":"Learning Overparameterized Neural Networks via Stochastic Gradient Descent on Structured Data","created":"2018-08-03","cited_by_count":261},{"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":"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":"1902.04674","title":"Towards moderate overparameterization: global convergence guarantees for training shallow neural networks","created":"2019-02-12","cited_by_count":176},{"id":"1602.05897","title":"Toward Deeper Understanding of Neural Networks: The Power of Initialization and a Dual View on Expressivity","created":"2016-02-18","cited_by_count":138},{"id":"1906.04688","title":"An Improved Analysis of Training Over-parameterized Deep Neural Networks","created":"2019-06-11","cited_by_count":121},{"id":"2302.13214","title":"Fast Attention Requires Bounded Entries","created":"2023-02-26","cited_by_count":102},{"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":"2112.07628","title":"Training Multi-Layer Over-Parametrized Neural Network in Subquadratic Time","created":"2021-12-14","cited_by_count":62},{"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":"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":"1704.08246","title":"Relative Error Tensor Low Rank Approximation","created":"2017-04-26","cited_by_count":45},{"id":"2303.16504","title":"An Over-parameterized Exponential Regression","created":"2023-03-29","cited_by_count":45},{"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":"2304.13276","title":"The Closeness of In-Context Learning and Weight Shifting for Softmax Regression","created":"2023-04-26","cited_by_count":41},{"id":"2304.02207","title":"Algorithm and Hardness for Dynamic Attention Maintenance in Large Language Models","created":"2023-04-05","cited_by_count":37},{"id":"2304.04397","title":"Randomized and Deterministic Attention Sparsification Algorithms for Over-parameterized Feature Dimension","created":"2023-04-10","cited_by_count":37},{"id":"2002.06668","title":"Over-parameterized Adversarial Training: An Analysis Overcoming the Curse of Dimensionality","created":"2020-02-16","cited_by_count":36},{"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":"2307.02419","title":"In-Context Learning for Attention Scheme: from Single Softmax Regression to Multiple Softmax Regression via a Tensor Trick","created":"2023-07-05","cited_by_count":32},{"id":"2306.04933","title":"InfoPrompt: Information-Theoretic Soft Prompt Tuning for Natural Language Understanding","created":"2023-06-08","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":"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":"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":"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":"1905.11580","title":"A near-optimal algorithm for approximating the John Ellipsoid","created":"2019-05-28","cited_by_count":23},{"id":"1911.09873","title":"Neural Networks Learning and Memorization with (almost) no Over-Parameterization","created":"2019-11-22","cited_by_count":23},{"id":"1805.07674","title":"BourGAN: Generative Networks with Metric Embeddings","created":"2018-05-19","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":"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":"2208.03635","title":"Federated Adversarial Learning: A Framework with Convergence Analysis","created":"2022-08-07","cited_by_count":17},{"id":"2206.12802","title":"Bounding the Width of Neural Networks via Coupled Initialization -- A Worst Case Analysis","created":"2022-06-26","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":"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":"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}],"next_cursor":null}