{"list":"other","total":60,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"1708.07747","title":"Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms","created":"2017-08-25","cited_by_count":4349},{"id":"1609.07843","title":"Pointer Sentinel Mixture Models","created":"2016-09-26","cited_by_count":3096},{"id":"1806.07572","title":"Neural Tangent Kernel: Convergence and Generalization in Neural Networks","created":"2018-06-20","cited_by_count":2621},{"id":"2005.00687","title":"Open Graph Benchmark: Datasets for Machine Learning on Graphs","created":"2020-05-02","cited_by_count":2163},{"id":"2304.01373","title":"Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling","created":"2023-04-03","cited_by_count":1786},{"id":"1611.03530","title":"Understanding deep learning requires rethinking generalization","created":"2016-11-10","cited_by_count":1674},{"id":"1806.01261","title":"Relational inductive biases, deep learning, and graph networks","created":"2018-06-04","cited_by_count":1360},{"id":"1712.09913","title":"Visualizing the Loss Landscape of Neural Nets","created":"2017-12-28","cited_by_count":1130},{"id":"1812.07956","title":"On Lazy Training in Differentiable Programming","created":"2018-12-19","cited_by_count":675},{"id":"1811.03804","title":"Gradient Descent Finds Global Minima of Deep Neural Networks","created":"2018-11-09","cited_by_count":574},{"id":"1904.11955","title":"On Exact Computation with an Infinitely Wide Neural Net","created":"2019-04-26","cited_by_count":573},{"id":"1608.04636","title":"Linear Convergence of Gradient and Proximal-Gradient Methods Under the Polyak-\\L{}ojasiewicz Condition","created":"2016-08-16","cited_by_count":539},{"id":"1811.08839","title":"fastMRI: An Open Dataset and Benchmarks for Accelerated MRI","created":"2018-11-21","cited_by_count":470},{"id":"1805.09545","title":"On the Global Convergence of Gradient Descent for Over-parameterized Models using Optimal Transport","created":"2018-05-24","cited_by_count":426},{"id":"1905.11881","title":"Why gradient clipping accelerates training: A theoretical justification for adaptivity","created":"2019-05-28","cited_by_count":341},{"id":"1906.00091","title":"Deep Learning Recommendation Model for Personalization and Recommendation Systems","created":"2019-05-31","cited_by_count":327},{"id":"1703.00887","title":"How to Escape Saddle Points Efficiently","created":"2017-03-02","cited_by_count":285},{"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":"1806.01811","title":"AdaGrad stepsizes: Sharp convergence over nonconvex landscapes","created":"2018-06-05","cited_by_count":182},{"id":"2301.11235","title":"Handbook of Convergence Theorems for (Stochastic) Gradient Methods","created":"2023-01-26","cited_by_count":163},{"id":"1810.07288","title":"Fast and Faster Convergence of SGD for Over-Parameterized Models and an Accelerated Perceptron","created":"2018-10-16","cited_by_count":143},{"id":"2002.03305","title":"Momentum Improves Normalized SGD","created":"2020-02-09","cited_by_count":139},{"id":"2002.10542","title":"Stochastic Polyak Step-size for SGD: An Adaptive Learning Rate for Fast Convergence","created":"2020-02-24","cited_by_count":137},{"id":"1712.08968","title":"Spurious Local Minima are Common in Two-Layer ReLU Neural Networks","created":"2017-12-24","cited_by_count":104},{"id":"1609.05191","title":"Gradient Descent Learns Linear Dynamical Systems","created":"2016-09-16","cited_by_count":79},{"id":"2107.11433","title":"A general sample complexity analysis of vanilla policy gradient","created":"2021-07-23","cited_by_count":76},{"id":"2309.10818","title":"SlimPajama-DC: Understanding Data Combinations for LLM Training","created":"2023-09-19","cited_by_count":72},{"id":"2006.10311","title":"SGD for Structured Nonconvex Functions: Learning Rates, Minibatching and Interpolation","created":"2020-06-18","cited_by_count":67},{"id":"1803.05999","title":"Escaping Saddles with Stochastic Gradients","created":"2018-03-15","cited_by_count":66},{"id":"2302.01734","title":"Stochastic Policy Gradient Methods: Improved Sample Complexity for Fisher-non-degenerate Policies","created":"2023-02-03","cited_by_count":58},{"id":"2306.07179","title":"Benchmarking Neural Network Training Algorithms","created":"2023-06-12","cited_by_count":52},{"id":"1904.06963","title":"The Impact of Neural Network Overparameterization on Gradient Confusion and Stochastic Gradient Descent","created":"2019-04-15","cited_by_count":46},{"id":"1510.08234","title":"From error bounds to the complexity of first-order descent methods for convex functions","created":"2015-10-28","cited_by_count":43},{"id":"2205.04583","title":"Dynamics of SGD with Stochastic Polyak Stepsizes: Truly Adaptive Variants and Convergence to Exact Solution","created":"2022-05-09","cited_by_count":40},{"id":"1705.10499","title":"Online to Offline Conversions, Universality and Adaptive Minibatch Sizes","created":"2017-05-30","cited_by_count":39},{"id":"1901.00451","title":"SGD Converges to Global Minimum in Deep Learning via Star-convex Path","created":"2019-01-02","cited_by_count":39},{"id":"1602.02915","title":"Calculus of the exponent of Kurdyka-{\\L}ojasiewicz inequality and its applications to linear convergence of first-order methods","created":"2016-02-09","cited_by_count":35},{"id":"2106.03970","title":"Batch Normalization Orthogonalizes Representations in Deep Random Networks","created":"2021-06-07","cited_by_count":29},{"id":"2311.03252","title":"Parameter-Agnostic Optimization under Relaxed Smoothness","created":"2023-11-06","cited_by_count":29},{"id":"1805.10694","title":"Exponential convergence rates for Batch Normalization: The power of length-direction decoupling in non-convex optimization","created":"2018-05-27","cited_by_count":27},{"id":"1311.1873","title":"An Asynchronous Parallel Stochastic Coordinate Descent Algorithm","created":"2013-11-08","cited_by_count":26},{"id":"2111.01875","title":"Subquadratic Overparameterization for Shallow Neural Networks","created":"2021-11-02","cited_by_count":26},{"id":"1303.4645","title":"Gradient methods for convex minimization: better rates under weaker conditions","created":"2013-03-19","cited_by_count":23},{"id":"2201.11066","title":"Server-Side Stepsizes and Sampling Without Replacement Provably Help in Federated Optimization","created":"2022-01-26","cited_by_count":23},{"id":"2306.02601","title":"Aiming towards the minimizers: fast convergence of SGD for overparametrized problems","created":"2023-06-05","cited_by_count":22},{"id":"2210.01748","title":"Sharp Analysis of Stochastic Optimization under Global Kurdyka-{\\L}ojasiewicz Inequality","created":"2022-10-04","cited_by_count":20},{"id":"2211.00188","title":"Adaptive Compression for Communication-Efficient Distributed Training","created":"2022-10-31","cited_by_count":16},{"id":"2310.20452","title":"AsGrad: A Sharp Unified Analysis of Asynchronous-SGD Algorithms","created":"2023-10-31","cited_by_count":16},{"id":"2305.06927","title":"Convergence of Alternating Gradient Descent for Matrix Factorization","created":"2023-05-11","cited_by_count":12},{"id":"2305.18929","title":"Clip21: Error Feedback for Gradient Clipping","created":"2023-05-30","cited_by_count":11},{"id":"2407.04358","title":"An Adaptive Stochastic Gradient Method with Non-negative Gauss-Newton Stepsizes","created":"2024-07-05","cited_by_count":10},{"id":"2306.11922","title":"No Wrong Turns: The Simple Geometry Of Neural Networks Optimization Paths","created":"2023-06-20","cited_by_count":7},{"id":"2303.00096","title":"Fast convergence to non-isolated minima: four equivalent conditions for $\\mathrm{C}^2$ functions","created":"2023-02-28","cited_by_count":6},{"id":"2407.01825","title":"Reevaluating Theoretical Analysis Methods for Optimization in Deep Learning","created":"2024-07-01","cited_by_count":3}],"next_cursor":null}