{"list":"other","total":52,"rows":[{"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":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"1411.7766","title":"Deep Learning Face Attributes in the Wild","created":"2014-11-28","cited_by_count":3693},{"id":"1907.02893","title":"Invariant Risk Minimization","created":"2019-07-05","cited_by_count":1854},{"id":"1911.08731","title":"Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization","created":"2019-11-20","cited_by_count":1247},{"id":"1901.05555","title":"Class-Balanced Loss Based on Effective Number of Samples","created":"2019-01-16","cited_by_count":1245},{"id":"1706.07522","title":"Deep Hashing Network for Unsupervised Domain Adaptation","created":"2017-06-22","cited_by_count":1188},{"id":"2007.01434","title":"In Search of Lost Domain Generalization","created":"2020-07-02","cited_by_count":1054},{"id":"1710.03077","title":"Deeper, Broader and Artier Domain Generalization","created":"2017-10-09","cited_by_count":986},{"id":"2003.00688","title":"Out-of-Distribution Generalization via Risk Extrapolation (REx)","created":"2020-03-02","cited_by_count":742},{"id":"2202.10054","title":"Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution","created":"2022-02-21","cited_by_count":739},{"id":"2107.09044","title":"Just Train Twice: Improving Group Robustness without Training Group Information","created":"2021-07-19","cited_by_count":523},{"id":"1710.05381","title":"A systematic study of the class imbalance problem in convolutional neural networks","created":"2017-10-15","cited_by_count":513},{"id":"2204.02937","title":"Last Layer Re-Training is Sufficient for Robustness to Spurious Correlations","created":"2022-04-06","cited_by_count":381},{"id":"1806.08010","title":"Fairness Without Demographics in Repeated Loss Minimization","created":"2018-06-20","cited_by_count":364},{"id":"1802.06309","title":"Learning Adversarially Fair and Transferable Representations","created":"2018-02-17","cited_by_count":353},{"id":"2006.07710","title":"The Pitfalls of Simplicity Bias in Neural Networks","created":"2020-06-13","cited_by_count":351},{"id":"1705.09280","title":"Implicit Regularization in Matrix Factorization","created":"2017-05-25","cited_by_count":322},{"id":"2005.04345","title":"An Investigation of Why Overparameterization Exacerbates Spurious Correlations","created":"2020-05-09","cited_by_count":310},{"id":"1803.11364","title":"Joint Optimization Framework for Learning with Noisy Labels","created":"2018-03-30","cited_by_count":293},{"id":"1802.06509","title":"On the Optimization of Deep Networks: Implicit Acceleration by Overparameterization","created":"2018-02-19","cited_by_count":284},{"id":"2102.06810","title":"Understanding self-supervised Learning Dynamics without Contrastive Pairs","created":"2021-02-12","cited_by_count":256},{"id":"1805.12317","title":"Multiaccuracy: Black-Box Post-Processing for Fairness in Classification","created":"2018-05-31","cited_by_count":222},{"id":"2002.09434","title":"Few-Shot Learning via Learning the Representation, Provably","created":"2020-02-21","cited_by_count":214},{"id":"2201.00299","title":"Improving Out-of-Distribution Robustness via Selective Augmentation","created":"2022-01-02","cited_by_count":202},{"id":"1608.08868","title":"Demographic Dialectal Variation in Social Media: A Case Study of African-American English","created":"2016-08-31","cited_by_count":196},{"id":"2006.11650","title":"On the Theory of Transfer Learning: The Importance of Task Diversity","created":"2020-06-20","cited_by_count":186},{"id":"1806.00900","title":"Algorithmic Regularization in Learning Deep Homogeneous Models: Layers are Automatically Balanced","created":"2018-06-04","cited_by_count":177},{"id":"2203.01517","title":"Correct-N-Contrast: A Contrastive Approach for Improving Robustness to Spurious Correlations","created":"2022-03-03","cited_by_count":172},{"id":"2002.11684","title":"Provable Meta-Learning of Linear Representations","created":"2020-02-26","cited_by_count":161},{"id":"1610.02581","title":"Variance-based regularization with convex objectives","created":"2016-10-08","cited_by_count":155},{"id":"1904.12191","title":"Linearized two-layers neural networks in high dimension","created":"2019-04-27","cited_by_count":155},{"id":"2008.01064","title":"Predicting What You Already Know Helps: Provable Self-Supervised Learning","created":"2020-08-03","cited_by_count":152},{"id":"1909.02060","title":"Distributionally Robust Language Modeling","created":"2019-09-04","cited_by_count":143},{"id":"1904.13262","title":"Implicit Regularization of Discrete Gradient Dynamics in Linear Neural Networks","created":"2019-04-30","cited_by_count":124},{"id":"1812.08233","title":"Invariance, Causality and Robustness","created":"2018-12-19","cited_by_count":123},{"id":"1701.01619","title":"Learning From Noisy Large-Scale Datasets With Minimal Supervision","created":"2017-01-06","cited_by_count":115},{"id":"2103.07756","title":"Learning with Feature-Dependent Label Noise: A Progressive Approach","created":"2021-03-13","cited_by_count":102},{"id":"2202.04414","title":"Agree to Disagree: Diversity through Disagreement for Better Transferability","created":"2022-02-09","cited_by_count":70},{"id":"1810.10082","title":"A Continuous-Time View of Early Stopping for Least Squares","created":"2018-10-23","cited_by_count":69},{"id":"2106.07171","title":"Examining and Combating Spurious Features under Distribution Shift","created":"2021-06-14","cited_by_count":65},{"id":"2210.05775","title":"C-Mixup: Improving Generalization in Regression","created":"2022-10-11","cited_by_count":57},{"id":"2110.02473","title":"The Power of Contrast for Feature Learning: A Theoretical Analysis","created":"2021-10-06","cited_by_count":53},{"id":"2106.02695","title":"Meta-Learning with Fewer Tasks through Task Interpolation","created":"2021-06-04","cited_by_count":45},{"id":"2106.10189","title":"Adversarial Training Helps Transfer Learning via Better Representations","created":"2021-06-18","cited_by_count":36},{"id":"2101.07732","title":"Out-of-distribution Prediction with Invariant Risk Minimization: The Limitation and An Effective Fix","created":"2021-01-16","cited_by_count":27},{"id":"2203.15664","title":"Nearly Minimax Algorithms for Linear Bandits with Shared Representation","created":"2022-03-29","cited_by_count":16},{"id":"1704.07016","title":"Using SVD for Topic Modeling","created":"2017-04-24","cited_by_count":14},{"id":"2106.14836","title":"Understanding Dynamics of Nonlinear Representation Learning and Its Application","created":"2021-06-28","cited_by_count":11},{"id":"2106.09777","title":"On Invariance Penalties for Risk Minimization","created":"2021-06-17","cited_by_count":10},{"id":"2111.03135","title":"Scaffolding Sets","created":"2021-11-04","cited_by_count":8}],"next_cursor":null}