{"list":"other","total":58,"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":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1409.4842","title":"Going Deeper with Convolutions","created":"2014-09-17","cited_by_count":4241},{"id":"1904.09751","title":"The Curious Case of Neural Text Degeneration","created":"2019-04-22","cited_by_count":2916},{"id":"2005.08100","title":"Conformer: Convolution-augmented Transformer for Speech Recognition","created":"2020-05-16","cited_by_count":1863},{"id":"1611.03530","title":"Understanding deep learning requires rethinking generalization","created":"2016-11-10","cited_by_count":1674},{"id":"1902.10811","title":"Do ImageNet Classifiers Generalize to ImageNet?","created":"2019-02-13","cited_by_count":1515},{"id":"2010.01412","title":"Sharpness-Aware Minimization for Efficiently Improving Generalization","created":"2020-10-03","cited_by_count":1417},{"id":"2206.14858","title":"Solving Quantitative Reasoning Problems with Language Models","created":"2022-06-29","cited_by_count":1392},{"id":"2211.09085","title":"Galactica: A Large Language Model for Science","created":"2022-11-16","cited_by_count":744},{"id":"2207.01848","title":"TabPFN: A Transformer That Solves Small Tabular Classification Problems in a Second","created":"2022-07-05","cited_by_count":674},{"id":"2107.14795","title":"Perceiver IO: A General Architecture for Structured Inputs & Outputs","created":"2021-07-30","cited_by_count":629},{"id":"1703.11008","title":"Computing Nonvacuous Generalization Bounds for Deep (Stochastic) Neural Networks with Many More Parameters than Training Data","created":"2017-03-31","cited_by_count":533},{"id":"2002.08791","title":"Bayesian Deep Learning and a Probabilistic Perspective of Generalization","created":"2020-02-20","cited_by_count":480},{"id":"2112.10510","title":"Transformers Can Do Bayesian Inference","created":"2021-12-20","cited_by_count":360},{"id":"2106.01342","title":"SAINT: Improved Neural Networks for Tabular Data via Row Attention and Contrastive Pre-Training","created":"2021-06-02","cited_by_count":319},{"id":"2104.14421","title":"What Are Bayesian Neural Network Posteriors Really Like?","created":"2021-04-29","cited_by_count":308},{"id":"1802.05296","title":"Stronger generalization bounds for deep nets via a compression approach","created":"2018-02-14","cited_by_count":307},{"id":"2210.10749","title":"Transformers Learn Shortcuts to Automata","created":"2022-10-19","cited_by_count":268},{"id":"2110.11216","title":"User-friendly introduction to PAC-Bayes bounds","created":"2021-10-21","cited_by_count":239},{"id":"2201.09792","title":"Patches Are All You Need?","created":"2022-01-24","cited_by_count":201},{"id":"2207.08815","title":"Why do tree-based models still outperform deep learning on tabular data?","created":"2022-07-18","cited_by_count":199},{"id":"2104.09459","title":"A Practical Method for Constructing Equivariant Multilayer Perceptrons for Arbitrary Matrix Groups","created":"2021-04-19","cited_by_count":187},{"id":"1805.08522","title":"Deep learning generalizes because the parameter-function map is biased towards simple functions","created":"2018-05-22","cited_by_count":183},{"id":"2103.10427","title":"The Low-Rank Simplicity Bias in Deep Networks","created":"2021-03-18","cited_by_count":154},{"id":"1710.05468","title":"Generalization in Deep Learning","created":"2017-10-16","cited_by_count":146},{"id":"1710.06451","title":"A Bayesian Perspective on Generalization and Stochastic Gradient Descent","created":"2017-10-17","cited_by_count":135},{"id":"1302.4245","title":"Gaussian Process Kernels for Pattern Discovery and Extrapolation","created":"2013-02-18","cited_by_count":132},{"id":"1804.05862","title":"Non-Vacuous Generalization Bounds at the ImageNet Scale: A PAC-Bayesian Compression Approach","created":"2018-04-16","cited_by_count":126},{"id":"2112.13492","title":"Vision Transformer for Small-Size Datasets","created":"2021-12-27","cited_by_count":122},{"id":"2106.04537","title":"Can You Learn an Algorithm? Generalizing from Easy to Hard Problems with Recurrent Networks","created":"2021-06-08","cited_by_count":117},{"id":"2007.12911","title":"Tighter risk certificates for neural networks","created":"2020-07-25","cited_by_count":112},{"id":"2003.01897","title":"Optimal Regularization Can Mitigate Double Descent","created":"2020-03-04","cited_by_count":109},{"id":"1605.08636","title":"PAC-Bayesian Theory Meets Bayesian Inference","created":"2016-05-27","cited_by_count":88},{"id":"2012.14660","title":"A Theoretical Analysis of the Repetition Problem in Text Generation","created":"2020-12-29","cited_by_count":83},{"id":"1712.09376","title":"Entropy-SGD optimizes the prior of a PAC-Bayes bound: Generalization properties of Entropy-SGD and data-dependent priors","created":"2017-12-26","cited_by_count":81},{"id":"2211.13609","title":"PAC-Bayes Compression Bounds So Tight That They Can Explain Generalization","created":"2022-11-24","cited_by_count":76},{"id":"2112.01388","title":"Residual Pathway Priors for Soft Equivariance Constraints","created":"2021-12-02","cited_by_count":75},{"id":"1802.07044","title":"The Description Length of Deep Learning Models","created":"2018-02-20","cited_by_count":72},{"id":"2006.10929","title":"On the role of data in PAC-Bayes bounds","created":"2020-06-19","cited_by_count":64},{"id":"2109.14119","title":"Stochastic Training is Not Necessary for Generalization","created":"2021-09-29","cited_by_count":63},{"id":"2202.11678","title":"Bayesian Model Selection, the Marginal Likelihood, and Generalization","created":"2022-02-23","cited_by_count":57},{"id":"2010.11939","title":"Limitations of Autoregressive Models and Their Alternatives","created":"2020-10-22","cited_by_count":55},{"id":"1906.03291","title":"Understanding Generalization through Visualizations","created":"2019-06-07","cited_by_count":54},{"id":"2003.12843","title":"A Close Look at Deep Learning with Small Data","created":"2020-03-28","cited_by_count":54},{"id":"2201.04600","title":"Deep Symbolic Regression for Recurrent Sequences","created":"2022-01-12","cited_by_count":54},{"id":"2210.02984","title":"The Lie Derivative for Measuring Learned Equivariance","created":"2022-10-06","cited_by_count":54},{"id":"2003.02139","title":"Rethinking Parameter Counting in Deep Models: Effective Dimensionality Revisited","created":"2020-03-04","cited_by_count":51},{"id":"1905.12213","title":"Where is the Information in a Deep Neural Network?","created":"2019-05-29","cited_by_count":42},{"id":"1402.4304","title":"Automatic Construction and Natural-Language Description of Nonparametric Regression Models","created":"2014-02-18","cited_by_count":40},{"id":"2102.01117","title":"SGD Generalizes Better Than GD (And Regularization Doesn't Help)","created":"2021-02-01","cited_by_count":38},{"id":"1904.03292","title":"The Information Complexity of Learning Tasks, their Structure and their Distance","created":"2019-04-05","cited_by_count":36},{"id":"1909.11522","title":"Neural networks are a priori biased towards Boolean functions with low entropy","created":"2019-09-25","cited_by_count":24},{"id":"1910.13565","title":"Function-Space Distributions over Kernels","created":"2019-10-29","cited_by_count":17},{"id":"2111.05321","title":"Turing-Universal Learners with Optimal Scaling Laws","created":"2021-11-09","cited_by_count":4}],"next_cursor":null}