{"list":"other","total":74,"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":"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":"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":"1710.09412","title":"mixup: Beyond Empirical Risk Minimization","created":"2017-10-25","cited_by_count":5183},{"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":"1703.03400","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","created":"2017-03-09","cited_by_count":4897},{"id":"1606.08415","title":"Gaussian Error Linear Units (GELUs)","created":"2016-06-27","cited_by_count":3502},{"id":"1907.10902","title":"Optuna: A Next-generation Hyperparameter Optimization Framework","created":"2019-07-25","cited_by_count":2501},{"id":"2001.07685","title":"FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence","created":"2020-01-21","cited_by_count":2085},{"id":"1611.03530","title":"Understanding deep learning requires rethinking generalization","created":"2016-11-10","cited_by_count":1674},{"id":"2010.01412","title":"Sharpness-Aware Minimization for Efficiently Improving Generalization","created":"2020-10-03","cited_by_count":1417},{"id":"1812.01754","title":"Moment Matching for Multi-Source Domain Adaptation","created":"2018-12-04","cited_by_count":1331},{"id":"1906.02629","title":"When Does Label Smoothing Help?","created":"2019-06-06","cited_by_count":988},{"id":"1706.05098","title":"An Overview of Multi-Task Learning in Deep Neural Networks","created":"2017-06-15","cited_by_count":803},{"id":"2109.01903","title":"Robust fine-tuning of zero-shot models","created":"2021-09-04","cited_by_count":797},{"id":"1706.08498","title":"Spectrally-normalized margin bounds for neural networks","created":"2017-06-26","cited_by_count":686},{"id":"1609.03683","title":"Making Deep Neural Networks Robust to Label Noise: a Loss Correction Approach","created":"2016-09-13","cited_by_count":665},{"id":"2007.08199","title":"Learning from Noisy Labels with Deep Neural Networks: A Survey","created":"2020-07-16","cited_by_count":582},{"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":"1912.02178","title":"Fantastic Generalization Measures and Where to Find Them","created":"2019-12-04","cited_by_count":513},{"id":"2007.00151","title":"Early-Learning Regularization Prevents Memorization of Noisy Labels","created":"2020-06-30","cited_by_count":416},{"id":"1501.01571","title":"An Introduction to Matrix Concentration Inequalities","created":"2015-01-07","cited_by_count":397},{"id":"2008.11687","title":"What is being transferred in transfer learning?","created":"2020-08-26","cited_by_count":368},{"id":"1901.11504","title":"Multi-Task Deep Neural Networks for Natural Language Understanding","created":"2019-01-31","cited_by_count":350},{"id":"1707.09564","title":"A PAC-Bayesian Approach to Spectrally-Normalized Margin Bounds for Neural Networks","created":"2017-07-29","cited_by_count":314},{"id":"1703.02930","title":"Nearly-tight VC-dimension and pseudodimension bounds for piecewise linear neural networks","created":"2017-03-08","cited_by_count":311},{"id":"1802.05296","title":"Stronger generalization bounds for deep nets via a compression approach","created":"2018-02-14","cited_by_count":307},{"id":"1901.10159","title":"An Investigation into Neural Net Optimization via Hessian Eigenvalue Density","created":"2019-01-29","cited_by_count":292},{"id":"1912.07145","title":"PyHessian: Neural Networks Through the Lens of the Hessian","created":"2019-12-16","cited_by_count":292},{"id":"2011.01403","title":"Supervised Contrastive Learning for Pre-trained Language Model Fine-tuning","created":"2020-11-03","cited_by_count":276},{"id":"2006.13554","title":"Normalized Loss Functions for Deep Learning with Noisy Labels","created":"2020-06-24","cited_by_count":257},{"id":"2110.11216","title":"User-friendly introduction to PAC-Bayes bounds","created":"2021-10-21","cited_by_count":239},{"id":"1802.01483","title":"Explicit Inductive Bias for Transfer Learning with Convolutional Networks","created":"2018-02-05","cited_by_count":227},{"id":"1906.00189","title":"Are Anchor Points Really Indispensable in Label-Noise Learning?","created":"2019-06-01","cited_by_count":208},{"id":"2003.02819","title":"Does label smoothing mitigate label noise?","created":"2020-03-05","cited_by_count":204},{"id":"2006.11650","title":"On the Theory of Transfer Learning: The Importance of Task Diversity","created":"2020-06-20","cited_by_count":186},{"id":"1611.07476","title":"Eigenvalues of the Hessian in Deep Learning: Singularity and Beyond","created":"2016-11-22","cited_by_count":159},{"id":"1903.11680","title":"Gradient Descent with Early Stopping is Provably Robust to Label Noise for Overparameterized Neural Networks","created":"2019-03-27","cited_by_count":159},{"id":"1805.12076","title":"Towards Understanding the Role of Over-Parametrization in Generalization of Neural Networks","created":"2018-05-30","cited_by_count":142},{"id":"2006.07805","title":"Dual T: Reducing Estimation Error for Transition Matrix in Label-noise Learning","created":"2020-06-14","cited_by_count":142},{"id":"1901.05353","title":"A Primer on PAC-Bayesian Learning","created":"2019-01-16","cited_by_count":132},{"id":"2005.00770","title":"Exploring and Predicting Transferability across NLP Tasks","created":"2020-05-02","cited_by_count":128},{"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":"2002.10319","title":"Self-Adaptive Training: beyond Empirical Risk Minimization","created":"2020-02-24","cited_by_count":126},{"id":"2106.06530","title":"Label Noise SGD Provably Prefers Flat Global Minimizers","created":"2021-06-11","cited_by_count":121},{"id":"2005.00944","title":"Understanding and Improving Information Transfer in Multi-Task Learning","created":"2020-05-02","cited_by_count":114},{"id":"1902.03736","title":"A Short Note on Concentration Inequalities for Random Vectors with SubGaussian Norm","created":"2019-02-11","cited_by_count":106},{"id":"2012.07690","title":"A PAC-Bayesian Approach to Generalization Bounds for Graph Neural Networks","created":"2020-12-14","cited_by_count":85},{"id":"1901.09229","title":"DELTA: DEep Learning Transfer using Feature Map with Attention for Convolutional Networks","created":"2019-01-26","cited_by_count":80},{"id":"2105.04522","title":"Generalized Jensen-Shannon Divergence Loss for Learning with Noisy Labels","created":"2021-05-10","cited_by_count":74},{"id":"1901.08244","title":"Measurements of Three-Level Hierarchical Structure in the Outliers in the Spectrum of Deepnet Hessians","created":"2019-01-24","cited_by_count":68},{"id":"2002.04747","title":"On the Value of Target Data in Transfer Learning","created":"2020-02-12","cited_by_count":65},{"id":"2006.10929","title":"On the role of data in PAC-Bayes bounds","created":"2020-06-19","cited_by_count":64},{"id":"1901.04653","title":"Normalized Flat Minima: Exploring Scale Invariant Definition of Flat Minima for Neural Networks using PAC-Bayesian Analysis","created":"2019-01-15","cited_by_count":59},{"id":"1905.12600","title":"Generalization bounds for deep convolutional neural networks","created":"2019-05-29","cited_by_count":59},{"id":"1910.04284","title":"Improved Sample Complexities for Deep Networks and Robust Classification via an All-Layer Margin","created":"2019-10-09","cited_by_count":56},{"id":"1901.01672","title":"Generalization in Deep Networks: The Role of Distance from Initialization","created":"2019-01-07","cited_by_count":51},{"id":"1905.13344","title":"Deterministic PAC-Bayesian generalization bounds for deep networks via generalizing noise-resilience","created":"2019-05-30","cited_by_count":51},{"id":"1712.04577","title":"Learning From Noisy Singly-labeled Data","created":"2017-12-13","cited_by_count":50},{"id":"2002.08253","title":"Distance-Based Regularisation of Deep Networks for Fine-Tuning","created":"2020-02-19","cited_by_count":48},{"id":"2005.00695","title":"On the Generalization Effects of Linear Transformations in Data Augmentation","created":"2020-05-02","cited_by_count":47},{"id":"2010.04261","title":"Dissecting Hessian: Understanding Common Structure of Hessian in Neural Networks","created":"2020-10-08","cited_by_count":45},{"id":"2111.04578","title":"Improved Regularization and Robustness for Fine-tuning in Neural Networks","created":"2021-11-08","cited_by_count":45},{"id":"1307.2118","title":"A PAC-Bayesian Tutorial with A Dropout Bound","created":"2013-07-08","cited_by_count":43},{"id":"2106.12108","title":"Near-Optimal Linear Regression under Distribution Shift","created":"2021-06-23","cited_by_count":42},{"id":"1707.09920","title":"Regularization techniques for fine-tuning in neural machine translation","created":"2017-07-31","cited_by_count":27},{"id":"2010.11750","title":"Precise High-Dimensional Asymptotics for Quantifying Heterogeneous Transfers","created":"2020-10-22","cited_by_count":27},{"id":"2107.01641","title":"A Theoretical Analysis of Fine-tuning with Linear Teachers","created":"2021-07-04","cited_by_count":17},{"id":"2102.05242","title":"Patterns, predictions, and actions: A story about machine learning","created":"2021-02-10","cited_by_count":14},{"id":"2110.14163","title":"Does the Data Induce Capacity Control in Deep Learning?","created":"2021-10-27","cited_by_count":14},{"id":"2111.08190","title":"Learning Augmentation Distributions using Transformed Risk Minimization","created":"2021-11-16","cited_by_count":13}],"next_cursor":null}