{"list":"other","total":57,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"2103.03874","title":"Measuring Mathematical Problem Solving With the MATH Dataset","created":"2021-03-05","cited_by_count":5371},{"id":"1612.01474","title":"Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles","created":"2016-12-05","cited_by_count":3926},{"id":"1610.02136","title":"A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks","created":"2016-10-07","cited_by_count":2385},{"id":"2006.16241","title":"The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization","created":"2020-06-29","cited_by_count":1850},{"id":"1902.10811","title":"Do ImageNet Classifiers Generalize to ImageNet?","created":"2019-02-13","cited_by_count":1515},{"id":"1907.07174","title":"Natural Adversarial Examples","created":"2019-07-16","cited_by_count":1408},{"id":"1706.02690","title":"Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networks","created":"2017-06-08","cited_by_count":1328},{"id":"1906.02530","title":"Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shift","created":"2019-06-06","cited_by_count":1287},{"id":"1905.13549","title":"Learning Robust Global Representations by Penalizing Local Predictive Power","created":"2019-05-29","cited_by_count":1013},{"id":"2105.09938","title":"Measuring Coding Challenge Competence With APPS","created":"2021-05-20","cited_by_count":902},{"id":"1705.08500","title":"Selective Classification for Deep Neural Networks","created":"2017-05-23","cited_by_count":852},{"id":"1812.05159","title":"An Empirical Study of Example Forgetting during Deep Neural Network Learning","created":"2018-12-12","cited_by_count":678},{"id":"1912.02292","title":"Deep Double Descent: Where Bigger Models and More Data Hurt","created":"2019-12-04","cited_by_count":672},{"id":"2201.02177","title":"Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets","created":"2022-01-06","cited_by_count":629},{"id":"1604.03540","title":"Training Region-based Object Detectors with Online Hard Example Mining","created":"2016-04-12","cited_by_count":579},{"id":"2010.14701","title":"Scaling Laws for Autoregressive Generative Modeling","created":"2020-10-28","cited_by_count":522},{"id":"2103.14749","title":"Pervasive Label Errors in Test Sets Destabilize Machine Learning Benchmarks","created":"2021-03-26","cited_by_count":395},{"id":"1707.08819","title":"A Downsampled Variant of ImageNet as an Alternative to the CIFAR datasets","created":"2017-07-27","cited_by_count":377},{"id":"1802.03916","title":"Detecting and Correcting for Label Shift with Black Box Predictors","created":"2018-02-12","cited_by_count":366},{"id":"2102.06701","title":"Explaining Neural Scaling Laws","created":"2021-02-12","cited_by_count":363},{"id":"2003.07892","title":"Calibration of Pre-trained Transformers","created":"2020-03-17","cited_by_count":315},{"id":"2004.06100","title":"Pretrained Transformers Improve Out-of-Distribution Robustness","created":"2020-04-13","cited_by_count":294},{"id":"1904.03626","title":"On The Power of Curriculum Learning in Training Deep Networks","created":"2019-04-07","cited_by_count":286},{"id":"2001.10528","title":"Identifying Mislabeled Data using the Area Under the Margin Ranking","created":"2020-01-28","cited_by_count":261},{"id":"2107.04649","title":"Accuracy on the Line: On the Strong Correlation Between Out-of-Distribution and In-Distribution Generalization","created":"2021-07-09","cited_by_count":249},{"id":"1909.12673","title":"A Constructive Prediction of the Generalization Error Across Scales","created":"2019-09-27","cited_by_count":210},{"id":"1805.11783","title":"To Trust Or Not To Trust A Classifier","created":"2018-05-30","cited_by_count":207},{"id":"1905.11604","title":"SGD on Neural Networks Learns Functions of Increasing Complexity","created":"2019-05-28","cited_by_count":204},{"id":"1911.05248","title":"What Do Compressed Deep Neural Networks Forget?","created":"2019-11-13","cited_by_count":171},{"id":"2201.04234","title":"Leveraging Unlabeled Data to Predict Out-of-Distribution Performance","created":"2022-01-11","cited_by_count":145},{"id":"2106.09647","title":"Deep Learning Through the Lens of Example Difficulty","created":"2021-06-17","cited_by_count":141},{"id":"2003.07554","title":"A Unified View of Label Shift Estimation","created":"2020-03-17","cited_by_count":119},{"id":"2107.03315","title":"Predicting with Confidence on Unseen Distributions","created":"2021-07-07","cited_by_count":116},{"id":"2003.01897","title":"Optimal Regularization Can Mitigate Double Descent","created":"2020-03-04","cited_by_count":109},{"id":"2003.12506","title":"Hybrid Models for Open Set Recognition","created":"2020-03-27","cited_by_count":109},{"id":"2007.02915","title":"Are Labels Always Necessary for Classifier Accuracy Evaluation?","created":"2020-07-06","cited_by_count":104},{"id":"2008.11600","title":"Estimating Example Difficulty Using Variance of Gradients","created":"2020-08-26","cited_by_count":97},{"id":"2202.08384","title":"Limitations of Neural Collapse for Understanding Generalization in Deep Learning","created":"2022-02-17","cited_by_count":63},{"id":"2110.12899","title":"No One Representation to Rule Them All: Overlapping Features of Training Methods","created":"2021-10-20","cited_by_count":58},{"id":"2004.10802","title":"A Neural Scaling Law from the Dimension of the Data Manifold","created":"2020-04-22","cited_by_count":52},{"id":"2009.08092","title":"Distributional Generalization: A New Kind of Generalization","created":"2020-09-17","cited_by_count":42},{"id":"1905.12580","title":"Model Similarity Mitigates Test Set Overuse","created":"2019-05-29","cited_by_count":38},{"id":"2105.06020","title":"Are Larger Pretrained Language Models Uniformly Better? Comparing Performance at the Instance Level","created":"2021-05-13","cited_by_count":34},{"id":"2111.07167","title":"The Three Stages of Learning Dynamics in High-Dimensional Kernel Methods","created":"2021-11-13","cited_by_count":22},{"id":"2005.07360","title":"Learning Rate Annealing Can Provably Help Generalization, Even for Convex Problems","created":"2020-05-15","cited_by_count":11},{"id":"2010.08127","title":"The Deep Bootstrap Framework: Good Online Learners are Good Offline Generalizers","created":"2020-10-16","cited_by_count":11},{"id":"1902.01086","title":"Computational Limitations in Robust Classification and Win-Win Results","created":"2019-02-04","cited_by_count":10},{"id":"1511.06558","title":"Near-Optimal UGC-hardness of Approximating Max k-CSP_R","created":"2015-11-20","cited_by_count":2},{"id":"1409.1666","title":"Fundamental Limits on Communication for Oblivious Updates in Storage Networks","created":"2014-09-05","cited_by_count":1},{"id":"1509.01858","title":"Optimal Systematic Distributed Storage Codes with Fast Encoding","created":"2015-09-06","cited_by_count":1},{"id":"1702.04811","title":"Understanding Deep Learning Performance through an Examination of Test Set Difficulty: A Psychometric Case Study","created":"2017-02-15","cited_by_count":1},{"id":"1807.06479","title":"Tracking the $\\ell_2$ Norm with Constant Update Time","created":"2018-07-17","cited_by_count":1}],"next_cursor":null}