{"list":"other","total":62,"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":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"1608.06993","title":"Densely Connected Convolutional Networks","created":"2016-08-25","cited_by_count":6720},{"id":"1804.07461","title":"GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding","created":"2018-04-20","cited_by_count":4899},{"id":"1409.4842","title":"Going Deeper with Convolutions","created":"2014-09-17","cited_by_count":4241},{"id":"1606.05250","title":"SQuAD: 100,000+ Questions for Machine Comprehension of Text","created":"2016-06-16","cited_by_count":4148},{"id":"2201.03545","title":"A ConvNet for the 2020s","created":"2022-01-10","cited_by_count":3579},{"id":"1605.07146","title":"Wide Residual Networks","created":"2016-05-23","cited_by_count":3070},{"id":"1704.05426","title":"A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference","created":"2017-04-18","cited_by_count":2682},{"id":"1311.3618","title":"Describing Textures in the Wild","created":"2013-11-14","cited_by_count":2125},{"id":"1905.00537","title":"SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems","created":"2019-05-02","cited_by_count":1729},{"id":"1612.06890","title":"CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning","created":"2016-12-20","cited_by_count":1457},{"id":"2203.05482","title":"Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time","created":"2022-03-10","cited_by_count":1396},{"id":"1708.00055","title":"SemEval-2017 Task 1: Semantic Textual Similarity - Multilingual and Cross-lingual Focused Evaluation","created":"2017-07-31","cited_by_count":1001},{"id":"1805.12471","title":"Neural Network Acceptability Judgments","created":"2018-05-31","cited_by_count":958},{"id":"1804.04235","title":"Adafactor: Adaptive Learning Rates with Sublinear Memory Cost","created":"2018-04-11","cited_by_count":905},{"id":"1904.09237","title":"On the Convergence of Adam and Beyond","created":"2019-04-19","cited_by_count":841},{"id":"1703.00121","title":"Remote Sensing Image Scene Classification: Benchmark and State of the Art","created":"2017-03-01","cited_by_count":797},{"id":"1904.00962","title":"Large Batch Optimization for Deep Learning: Training BERT in 76 minutes","created":"2019-04-01","cited_by_count":674},{"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":"1708.03888","title":"Large Batch Training of Convolutional Networks","created":"2017-08-13","cited_by_count":535},{"id":"2109.02846","title":"Datasets: A Community Library for Natural Language Processing","created":"2021-09-07","cited_by_count":530},{"id":"1802.09568","title":"Shampoo: Preconditioned Stochastic Tensor Optimization","created":"2018-02-26","cited_by_count":426},{"id":"1910.04867","title":"A Large-scale Study of Representation Learning with the Visual Task Adaptation Benchmark","created":"2019-10-01","cited_by_count":425},{"id":"1905.13736","title":"Unlabeled Data Improves Adversarial Robustness","created":"2019-05-31","cited_by_count":416},{"id":"1810.08240","title":"Time-uniform, nonparametric, nonasymptotic confidence sequences","created":"2018-10-18","cited_by_count":229},{"id":"1806.01811","title":"AdaGrad stepsizes: Sharp convergence over nonconvex landscapes","created":"2018-06-05","cited_by_count":182},{"id":"2010.05893","title":"Large-Scale Methods for Distributionally Robust Optimization","created":"2020-10-12","cited_by_count":179},{"id":"1803.06523","title":"Stochastic model-based minimization of weakly convex functions","created":"2018-03-17","cited_by_count":159},{"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":"1602.04128","title":"Coin Betting and Parameter-Free Online Learning","created":"2016-02-12","cited_by_count":133},{"id":"1802.06293","title":"Black-Box Reductions for Parameter-free Online Learning in Banach Spaces","created":"2018-02-17","cited_by_count":125},{"id":"1905.09997","title":"Painless Stochastic Gradient: Interpolation, Line-Search, and Convergence Rates","created":"2019-05-24","cited_by_count":119},{"id":"1802.06175","title":"An Alternative View: When Does SGD Escape Local Minima?","created":"2018-02-17","cited_by_count":115},{"id":"2301.07733","title":"Learning-Rate-Free Learning by D-Adaptation","created":"2023-01-18","cited_by_count":113},{"id":"2202.05791","title":"The Power of Adaptivity in SGD: Self-Tuning Step Sizes with Unbounded Gradients and Affine Variance","created":"2022-02-11","cited_by_count":61},{"id":"2002.12242","title":"Lipschitz and Comparator-Norm Adaptivity in Online Learning","created":"2020-02-27","cited_by_count":57},{"id":"1905.00313","title":"Revisiting the Polyak step size","created":"2019-05-01","cited_by_count":55},{"id":"2205.02160","title":"Making SGD Parameter-Free","created":"2022-05-04","cited_by_count":50},{"id":"2002.03432","title":"On the distance between two neural networks and the stability of learning","created":"2020-02-09","cited_by_count":46},{"id":"1906.05661","title":"Training Neural Networks for and by Interpolation","created":"2019-06-13","cited_by_count":45},{"id":"2203.00444","title":"Parameter-free Mirror Descent","created":"2022-02-26","cited_by_count":45},{"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":"2002.04726","title":"Online Learning with Imperfect Hints","created":"2020-02-11","cited_by_count":37},{"id":"1906.11985","title":"Near-Optimal Methods for Minimizing Star-Convex Functions and Beyond","created":"2019-06-27","cited_by_count":36},{"id":"1903.08619","title":"The importance of better models in stochastic optimization","created":"2019-03-20","cited_by_count":32},{"id":"1902.01500","title":"Parameter-Free Online Convex Optimization with Sub-Exponential Noise","created":"2019-02-05","cited_by_count":28},{"id":"2210.14355","title":"Parameter-free Regret in High Probability with Heavy Tails","created":"2022-10-25","cited_by_count":28},{"id":"1406.3816","title":"Simultaneous Model Selection and Optimization through Parameter-free Stochastic Learning","created":"2014-06-15","cited_by_count":27},{"id":"2102.00236","title":"Parameter-free Stochastic Optimization of Variationally Coherent Functions","created":"2021-01-30","cited_by_count":27},{"id":"2201.07877","title":"PDE-Based Optimal Strategy for Unconstrained Online Learning","created":"2022-01-19","cited_by_count":27},{"id":"1802.05074","title":"L4: Practical loss-based stepsize adaptation for deep learning","created":"2018-02-14","cited_by_count":26},{"id":"1706.06569","title":"A Unified Approach to Adaptive Regularization in Online and Stochastic Optimization","created":"2017-06-20","cited_by_count":19},{"id":"1902.07528","title":"Adaptive scale-invariant online algorithms for learning linear models","created":"2019-02-20","cited_by_count":19},{"id":"2006.07507","title":"Better Parameter-free Stochastic Optimization with ODE Updates for Coin-Betting","created":"2020-06-12","cited_by_count":19}],"next_cursor":null}