{"list":"other","total":107,"rows":[{"id":"2004.07780","title":"Shortcut Learning in Deep Neural Networks","created":"2020-04-16","cited_by_count":1969},{"id":"1907.02893","title":"Invariant Risk Minimization","created":"2019-07-05","cited_by_count":1854},{"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":"2202.12837","title":"Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?","created":"2022-02-25","cited_by_count":1434},{"id":"1811.12231","title":"ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness","created":"2018-11-29","cited_by_count":1432},{"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":"1806.08734","title":"On the Spectral Bias of Neural Networks","created":"2018-06-22","cited_by_count":1341},{"id":"1803.05407","title":"Averaging Weights Leads to Wider Optima and Better Generalization","created":"2018-03-14","cited_by_count":1209},{"id":"1607.01719","title":"Deep CORAL: Correlation Alignment for Deep Domain Adaptation","created":"2016-07-06","cited_by_count":1200},{"id":"2104.13478","title":"Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges","created":"2021-04-27","cited_by_count":1167},{"id":"1811.12359","title":"Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations","created":"2018-11-29","cited_by_count":941},{"id":"1902.01007","title":"Right for the Wrong Reasons: Diagnosing Syntactic Heuristics in Natural Language Inference","created":"2019-02-04","cited_by_count":876},{"id":"2109.01903","title":"Robust fine-tuning of zero-shot models","created":"2021-09-04","cited_by_count":797},{"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":"1812.05159","title":"An Empirical Study of Example Forgetting during Deep Neural Network Learning","created":"2018-12-12","cited_by_count":678},{"id":"1810.02054","title":"Gradient Descent Provably Optimizes Over-parameterized Neural Networks","created":"2018-10-04","cited_by_count":659},{"id":"1807.04975","title":"Recognition in Terra Incognita","created":"2018-07-13","cited_by_count":658},{"id":"1710.10345","title":"The Implicit Bias of Gradient Descent on Separable Data","created":"2017-10-27","cited_by_count":655},{"id":"1912.05671","title":"Linear Mode Connectivity and the Lottery Ticket Hypothesis","created":"2019-12-11","cited_by_count":637},{"id":"1802.10026","title":"Loss Surfaces, Mode Connectivity, and Fast Ensembling of DNNs","created":"2018-02-27","cited_by_count":588},{"id":"1811.03804","title":"Gradient Descent Finds Global Minima of Deep Neural Networks","created":"2018-11-09","cited_by_count":574},{"id":"1901.08584","title":"Fine-Grained Analysis of Optimization and Generalization for Overparameterized Two-Layer Neural Networks","created":"2019-01-24","cited_by_count":566},{"id":"1907.04809","title":"Variational Autoencoders and Nonlinear ICA: A Unifying Framework","created":"2019-07-10","cited_by_count":503},{"id":"2110.11309","title":"Fast Model Editing at Scale","created":"2021-10-21","cited_by_count":498},{"id":"2011.03395","title":"Underspecification Presents Challenges for Credibility in Modern Machine Learning","created":"2020-11-06","cited_by_count":496},{"id":"2209.04836","title":"Git Re-Basin: Merging Models modulo Permutation Symmetries","created":"2022-09-11","cited_by_count":471},{"id":"2007.00644","title":"Measuring Robustness to Natural Distribution Shifts in Image Classification","created":"2020-07-01","cited_by_count":454},{"id":"2204.02937","title":"Last Layer Re-Training is Sufficient for Robustness to Spurious Correlations","created":"2022-04-06","cited_by_count":381},{"id":"1811.08883","title":"Rethinking ImageNet Pre-training","created":"2018-11-21","cited_by_count":377},{"id":"2008.11687","title":"What is being transferred in transfer learning?","created":"2020-08-26","cited_by_count":368},{"id":"2006.07710","title":"The Pitfalls of Simplicity Bias in Neural Networks","created":"2020-06-13","cited_by_count":351},{"id":"2006.09994","title":"Noise or Signal: The Role of Image Backgrounds in Object Recognition","created":"2020-06-17","cited_by_count":343},{"id":"1803.00885","title":"Essentially No Barriers in Neural Network Energy Landscape","created":"2018-03-02","cited_by_count":330},{"id":"1906.05890","title":"Gradient Descent Maximizes the Margin of Homogeneous Neural Networks","created":"2019-06-13","cited_by_count":320},{"id":"2106.04619","title":"Self-Supervised Learning with Data Augmentations Provably Isolates Content from Style","created":"2021-06-08","cited_by_count":312},{"id":"2005.04345","title":"An Investigation of Why Overparameterization Exacerbates Spurious Correlations","created":"2020-05-09","cited_by_count":310},{"id":"2110.06296","title":"The Role of Permutation Invariance in Linear Mode Connectivity of Neural Networks","created":"2021-10-12","cited_by_count":291},{"id":"1802.06509","title":"On the Optimization of Deep Networks: Implicit Acceleration by Overparameterization","created":"2018-02-19","cited_by_count":284},{"id":"1605.06336","title":"Unsupervised Feature Extraction by Time-Contrastive Learning and Nonlinear ICA","created":"2016-05-20","cited_by_count":273},{"id":"2011.09468","title":"Gradient Starvation: A Learning Proclivity in Neural Networks","created":"2020-11-18","cited_by_count":267},{"id":"1806.00468","title":"Implicit Bias of Gradient Descent on Linear Convolutional Networks","created":"2018-06-01","cited_by_count":251},{"id":"2002.02886","title":"Weakly-Supervised Disentanglement Without Compromises","created":"2020-02-07","cited_by_count":239},{"id":"1605.07110","title":"Deep Learning without Poor Local Minima","created":"2016-05-23","cited_by_count":234},{"id":"1910.05653","title":"Model Fusion via Optimal Transport","created":"2019-10-12","cited_by_count":219},{"id":"2102.11107","title":"Towards Causal Representation Learning","created":"2021-02-22","cited_by_count":209},{"id":"1905.11604","title":"SGD on Neural Networks Learns Functions of Increasing Complexity","created":"2019-05-28","cited_by_count":204},{"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":"1806.00900","title":"Algorithmic Regularization in Learning Deep Homogeneous Models: Layers are Automatically Balanced","created":"2018-06-04","cited_by_count":177},{"id":"1911.05248","title":"What Do Compressed Deep Neural Networks Forget?","created":"2019-11-13","cited_by_count":171},{"id":"2110.11328","title":"A Fine-Grained Analysis on Distribution Shift","created":"2021-10-21","cited_by_count":171},{"id":"2004.00345","title":"Editable Neural Networks","created":"2020-04-01","cited_by_count":155},{"id":"2205.09739","title":"Diverse Weight Averaging for Out-of-Distribution Generalization","created":"2022-05-19","cited_by_count":148},{"id":"1807.08479","title":"Domain Generalization via Conditional Invariant Representation","created":"2018-07-23","cited_by_count":146},{"id":"2010.04495","title":"Linear Mode Connectivity in Multitask and Continual Learning","created":"2020-10-09","cited_by_count":145},{"id":"2210.11369","title":"On Feature Learning in the Presence of Spurious Correlations","created":"2022-10-20","cited_by_count":145},{"id":"2110.10832","title":"Ensemble of Averages: Improving Model Selection and Boosting Performance in Domain Generalization","created":"2021-10-21","cited_by_count":144},{"id":"2005.00060","title":"Bridging Mode Connectivity in Loss Landscapes and Adversarial Robustness","created":"2020-04-30","cited_by_count":132},{"id":"2105.12221","title":"Geometry of the Loss Landscape in Overparameterized Neural Networks: Symmetries and Invariances","created":"2021-05-25","cited_by_count":127},{"id":"2006.12433","title":"What shapes feature representations? Exploring datasets, architectures, and training","created":"2020-06-22","cited_by_count":126},{"id":"2007.10930","title":"Towards Nonlinear Disentanglement in Natural Data with Temporal Sparse Coding","created":"2020-07-21","cited_by_count":122},{"id":"1803.01905","title":"Convergence of Gradient Descent on Separable Data","created":"2018-03-05","cited_by_count":110},{"id":"1611.01540","title":"Topology and Geometry of Half-Rectified Network Optimization","created":"2016-11-04","cited_by_count":102},{"id":"1905.12506","title":"Are Disentangled Representations Helpful for Abstract Visual Reasoning?","created":"2019-05-29","cited_by_count":100},{"id":"2011.02268","title":"Causal Autoregressive Flows","created":"2020-11-04","cited_by_count":99},{"id":"2106.05200","title":"Independent mechanism analysis, a new concept?","created":"2021-06-09","cited_by_count":97},{"id":"2012.04728","title":"Neural Mechanics: Symmetry and Broken Conservation Laws in Deep Learning Dynamics","created":"2020-12-08","cited_by_count":96},{"id":"1905.06642","title":"The Incomplete Rosetta Stone Problem: Identifiability Results for Multi-View Nonlinear ICA","created":"2019-05-16","cited_by_count":86},{"id":"2102.10472","title":"Learning Neural Network Subspaces","created":"2021-02-20","cited_by_count":82},{"id":"2202.00661","title":"When Do Flat Minima Optimizers Work?","created":"2022-02-01","cited_by_count":78},{"id":"2102.13042","title":"Loss Surface Simplexes for Mode Connecting Volumes and Fast Ensembling","created":"2021-02-25","cited_by_count":75},{"id":"1704.08045","title":"The loss surface of deep and wide neural networks","created":"2017-04-26","cited_by_count":74},{"id":"2202.06856","title":"Domain-Adjusted Regression or: ERM May Already Learn Features Sufficient for Out-of-Distribution Generalization","created":"2022-02-14","cited_by_count":69},{"id":"1811.00401","title":"Excessive Invariance Causes Adversarial Vulnerability","created":"2018-11-01","cited_by_count":66},{"id":"2002.07867","title":"Global Convergence of Deep Networks with One Wide Layer Followed by Pyramidal Topology","created":"2020-02-18","cited_by_count":66},{"id":"2112.01008","title":"Editing a classifier by rewriting its prediction rules","created":"2021-12-02","cited_by_count":65},{"id":"1906.06247","title":"Explaining Landscape Connectivity of Low-cost Solutions for Multilayer Nets","created":"2019-06-14","cited_by_count":63},{"id":"2010.14407","title":"On the Transfer of Disentangled Representations in Realistic Settings","created":"2020-10-27","cited_by_count":63},{"id":"2006.14599","title":"The Surprising Simplicity of the Early-Time Learning Dynamics of Neural Networks","created":"2020-06-25","cited_by_count":58},{"id":"2110.03095","title":"Which Shortcut Cues Will DNNs Choose? A Study from the Parameter-Space Perspective","created":"2021-10-06","cited_by_count":57},{"id":"2202.03418","title":"Diversify and Disambiguate: Learning From Underspecified Data","created":"2022-02-07","cited_by_count":56},{"id":"2205.12411","title":"Linear Connectivity Reveals Generalization Strategies","created":"2022-05-24","cited_by_count":56},{"id":"1805.06576","title":"Mad Max: Affine Spline Insights into Deep Learning","created":"2018-05-17","cited_by_count":55},{"id":"2101.11604","title":"Shape or Texture: Understanding Discriminative Features in CNNs","created":"2021-01-27","cited_by_count":52},{"id":"1812.03253","title":"Counterfactuals uncover the modular structure of deep generative models","created":"2018-12-08","cited_by_count":51},{"id":"1901.07417","title":"On Connected Sublevel Sets in Deep Learning","created":"2019-01-22","cited_by_count":51},{"id":"2105.02716","title":"Noether's Learning Dynamics: Role of Symmetry Breaking in Neural Networks","created":"2021-05-06","cited_by_count":50},{"id":"1706.08606","title":"Cognitive Psychology for Deep Neural Networks: A Shape Bias Case Study","created":"2017-06-26","cited_by_count":46},{"id":"2102.12353","title":"Nonlinear Invariant Risk Minimization: A Causal Approach","created":"2021-02-24","cited_by_count":42},{"id":"1809.10749","title":"On the loss landscape of a class of deep neural networks with no bad local valleys","created":"2018-09-27","cited_by_count":38},{"id":"1905.12580","title":"Model Similarity Mitigates Test Set Overuse","created":"2019-05-29","cited_by_count":38},{"id":"2210.15031","title":"Characterizing Datapoints via Second-Split Forgetting","created":"2022-10-26","cited_by_count":37},{"id":"2206.07837","title":"Modeling the Data-Generating Process is Necessary for Out-of-Distribution Generalization","created":"2022-06-15","cited_by_count":34},{"id":"2202.03038","title":"Deep Networks on Toroids: Removing Symmetries Reveals the Structure of Flat Regions in the Landscape Geometry","created":"2022-02-07","cited_by_count":28},{"id":"2207.02598","title":"Predicting is not Understanding: Recognizing and Addressing Underspecification in Machine Learning","created":"2022-07-06","cited_by_count":26},{"id":"2111.03220","title":"Augmentations in Graph Contrastive Learning: Current Methodological Flaws & Towards Better Practices","created":"2021-11-05","cited_by_count":25},{"id":"1705.02212","title":"Group invariance principles for causal generative models","created":"2017-05-05","cited_by_count":20},{"id":"2102.02805","title":"How do Quadratic Regularizers Prevent Catastrophic Forgetting: The Role of Interpolation","created":"2021-02-04","cited_by_count":19},{"id":"1702.07360","title":"Neural Decision Trees","created":"2017-02-23","cited_by_count":17}],"next_cursor":"100"}