{"list":"other","total":93,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1703.03400","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","created":"2017-03-09","cited_by_count":4897},{"id":"1612.00796","title":"Overcoming catastrophic forgetting in neural networks","created":"2016-12-02","cited_by_count":4787},{"id":"1505.07818","title":"Domain-Adversarial Training of Neural Networks","created":"2015-05-28","cited_by_count":3044},{"id":"1603.08155","title":"Perceptual Losses for Real-Time Style Transfer and Super-Resolution","created":"2016-03-27","cited_by_count":2694},{"id":"1806.07572","title":"Neural Tangent Kernel: Convergence and Generalization in Neural Networks","created":"2018-06-20","cited_by_count":2621},{"id":"2004.07780","title":"Shortcut Learning in Deep Neural Networks","created":"2020-04-16","cited_by_count":1969},{"id":"1908.09635","title":"A Survey on Bias and Fairness in Machine Learning","created":"2019-08-23","cited_by_count":1917},{"id":"1706.08840","title":"Gradient Episodic Memory for Continual Learning","created":"2017-06-26","cited_by_count":1898},{"id":"1907.02893","title":"Invariant Risk Minimization","created":"2019-07-05","cited_by_count":1854},{"id":"2010.01412","title":"Sharpness-Aware Minimization for Efficiently Improving Generalization","created":"2020-10-03","cited_by_count":1417},{"id":"2012.07421","title":"WILDS: A Benchmark of in-the-Wild Distribution Shifts","created":"2020-12-14","cited_by_count":1375},{"id":"1812.01754","title":"Moment Matching for Multi-Source Domain Adaptation","created":"2018-12-04","cited_by_count":1331},{"id":"1502.02791","title":"Learning Transferable Features with Deep Adaptation Networks","created":"2015-02-10","cited_by_count":1329},{"id":"2001.06782","title":"Gradient Surgery for Multi-Task Learning","created":"2020-01-19","cited_by_count":1256},{"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":"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":"1503.05671","title":"Optimizing Neural Networks with Kronecker-factored Approximate Curvature","created":"2015-03-19","cited_by_count":796},{"id":"1710.03463","title":"Learning to Generalize: Meta-Learning for Domain Generalization","created":"2017-10-10","cited_by_count":763},{"id":"2003.00688","title":"Out-of-Distribution Generalization via Risk Extrapolation (REx)","created":"2020-03-02","cited_by_count":742},{"id":"1807.04975","title":"Recognition in Terra Incognita","created":"2018-07-13","cited_by_count":658},{"id":"1301.2115","title":"Domain Generalization via Invariant Feature Representation","created":"2013-01-10","cited_by_count":623},{"id":"1412.3474","title":"Deep Domain Confusion: Maximizing for Domain Invariance","created":"2014-12-10","cited_by_count":600},{"id":"1501.01332","title":"Causal inference using invariant prediction: identification and confidence intervals","created":"2015-01-06","cited_by_count":536},{"id":"2011.03395","title":"Underspecification Presents Challenges for Credibility in Modern Machine Learning","created":"2020-11-06","cited_by_count":496},{"id":"1703.04933","title":"Sharp Minima Can Generalize For Deep Nets","created":"2017-03-15","cited_by_count":466},{"id":"1412.1193","title":"New insights and perspectives on the natural gradient method","created":"2014-12-03","cited_by_count":443},{"id":"2102.08604","title":"SWAD: Domain Generalization by Seeking Flat Minima","created":"2021-02-17","cited_by_count":434},{"id":"2007.02454","title":"Self-Challenging Improves Cross-Domain Generalization","created":"2020-07-05","cited_by_count":426},{"id":"1511.05547","title":"Return of Frustratingly Easy Domain Adaptation","created":"2015-11-17","cited_by_count":391},{"id":"2006.07710","title":"The Pitfalls of Simplicity Bias in Neural Networks","created":"2020-06-13","cited_by_count":351},{"id":"2005.04345","title":"An Investigation of Why Overparameterization Exacerbates Spurious Correlations","created":"2020-05-09","cited_by_count":310},{"id":"2010.07249","title":"Environment Inference for Invariant Learning","created":"2020-10-14","cited_by_count":306},{"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":"1706.04454","title":"Empirical Analysis of the Hessian of Over-Parametrized Neural Networks","created":"2017-06-14","cited_by_count":290},{"id":"1711.04623","title":"Three Factors Influencing Minima in SGD","created":"2017-11-13","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":"2010.05761","title":"The Risks of Invariant Risk Minimization","created":"2020-10-12","cited_by_count":262},{"id":"2104.09937","title":"Gradient Matching for Domain Generalization","created":"2021-04-20","cited_by_count":258},{"id":"1508.07680","title":"Domain Generalization for Object Recognition with Multi-task Autoencoders","created":"2015-08-31","cited_by_count":253},{"id":"2106.06607","title":"Invariance Principle Meets Information Bottleneck for Out-of-Distribution Generalization","created":"2021-06-11","cited_by_count":220},{"id":"1812.04754","title":"Gradient Descent Happens in a Tiny Subspace","created":"2018-12-12","cited_by_count":217},{"id":"1905.12558","title":"Limitations of the Empirical Fisher Approximation for Natural Gradient Descent","created":"2019-05-29","cited_by_count":217},{"id":"1905.11604","title":"SGD on Neural Networks Learns Functions of Increasing Complexity","created":"2019-05-28","cited_by_count":204},{"id":"2001.00677","title":"Improve Unsupervised Domain Adaptation with Mixup Training","created":"2020-01-03","cited_by_count":185},{"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":"1711.07910","title":"Domain Generalization by Marginal Transfer Learning","created":"2017-11-21","cited_by_count":180},{"id":"1911.07661","title":"Domain Generalization Using a Mixture of Multiple Latent Domains","created":"2019-11-18","cited_by_count":170},{"id":"2008.06388","title":"Common pitfalls and recommendations for using machine learning to detect and prognosticate for COVID-19 using chest radiographs and CT scans","created":"2020-08-14","cited_by_count":158},{"id":"2104.07876","title":"Deep Stable Learning for Out-Of-Distribution Generalization","created":"2021-04-16","cited_by_count":153},{"id":"2104.10201","title":"Bayesian Optimization is Superior to Random Search for Machine Learning Hyperparameter Tuning: Analysis of the Black-Box Optimization Challenge 2020","created":"2021-04-20","cited_by_count":148},{"id":"1807.08479","title":"Domain Generalization via Conditional Invariant Representation","created":"2018-07-23","cited_by_count":146},{"id":"2102.10395","title":"On Calibration and Out-of-domain Generalization","created":"2021-02-20","cited_by_count":134},{"id":"2009.00329","title":"Learning explanations that are hard to vary","created":"2020-09-01","cited_by_count":132},{"id":"2003.09772","title":"Invariant Rationalization","created":"2020-03-22","cited_by_count":131},{"id":"2108.00708","title":"Group Fisher Pruning for Practical Network Compression","created":"2021-08-02","cited_by_count":131},{"id":"2101.01134","title":"Does Invariant Risk Minimization Capture Invariance?","created":"2021-01-04","cited_by_count":116},{"id":"2009.05448","title":"Heterogeneous Domain Generalization via Domain Mixup","created":"2020-09-11","cited_by_count":103},{"id":"1812.02224","title":"Adapting Auxiliary Losses Using Gradient Similarity","created":"2018-12-05","cited_by_count":100},{"id":"2007.03141","title":"Dual Mixup Regularized Learning for Adversarial Domain Adaptation","created":"2020-07-07","cited_by_count":99},{"id":"1801.05787","title":"Faster gaze prediction with dense networks and Fisher pruning","created":"2018-01-17","cited_by_count":94},{"id":"2105.03818","title":"Heterogeneous Risk Minimization","created":"2021-05-09","cited_by_count":90},{"id":"1903.03448","title":"Support and Invertibility in Domain-Invariant Representations","created":"2019-03-08","cited_by_count":87},{"id":"2105.05612","title":"Evading the Simplicity Bias: Training a Diverse Set of Models Discovers Solutions with Superior OOD Generalization","created":"2021-05-12","cited_by_count":83},{"id":"1806.05810","title":"Best sources forward: domain generalization through source-specific nets","created":"2018-06-15","cited_by_count":82},{"id":"2102.05262","title":"Input Similarity from the Neural Network Perspective","created":"2021-02-10","cited_by_count":79},{"id":"1912.10985","title":"BackPACK: Packing more into backprop","created":"2019-12-23","cited_by_count":78},{"id":"2010.04647","title":"Learning Invariant Representations and Risks for Semi-supervised Domain Adaptation","created":"2020-10-09","cited_by_count":69},{"id":"1907.10599","title":"A Fine-Grained Spectral Perspective on Neural Networks","created":"2019-07-24","cited_by_count":68},{"id":"2103.15796","title":"Adaptive Methods for Real-World Domain Generalization","created":"2021-03-29","cited_by_count":66},{"id":"2012.14193","title":"Catastrophic Fisher Explosion: Early Phase Fisher Matrix Impacts Generalization","created":"2020-12-28","cited_by_count":62},{"id":"2108.01621","title":"Domain Generalization via Gradient Surgery","created":"2021-08-03","cited_by_count":60},{"id":"2012.04550","title":"In-N-Out: Pre-Training and Self-Training using Auxiliary Information for Out-of-Distribution Robustness","created":"2020-12-08","cited_by_count":50},{"id":"2106.02266","title":"SAND-mask: An Enhanced Gradient Masking Strategy for the Discovery of Invariances in Domain Generalization","created":"2021-06-04","cited_by_count":50},{"id":"1901.09491","title":"Stiffness: A New Perspective on Generalization in Neural Networks","created":"2019-01-28","cited_by_count":46},{"id":"1904.06963","title":"The Impact of Neural Network Overparameterization on Gradient Confusion and Stochastic Gradient Descent","created":"2019-04-15","cited_by_count":46},{"id":"1906.07774","title":"On the interplay between noise and curvature and its effect on optimization and generalization","created":"2019-06-18","cited_by_count":44},{"id":"1907.10732","title":"Hessian based analysis of SGD for Deep Nets: Dynamics and Generalization","created":"2019-07-24","cited_by_count":37},{"id":"1910.06943","title":"The Local Elasticity of Neural Networks","created":"2019-10-15","cited_by_count":37},{"id":"2104.04128","title":"An Empirical Comparison of Instance Attribution Methods for NLP","created":"2021-04-09","cited_by_count":35},{"id":"1910.05992","title":"Pathological spectra of the Fisher information metric and its variants in deep neural networks","created":"2019-10-14","cited_by_count":32},{"id":"2007.04532","title":"A Study of Gradient Variance in Deep Learning","created":"2020-07-09","cited_by_count":28},{"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":"1905.05252","title":"Learning Novel Policies For Tasks","created":"2019-05-13","cited_by_count":20},{"id":"2006.07461","title":"Learning Causal Models Online","created":"2020-06-12","cited_by_count":18},{"id":"2106.02624","title":"ViViT: Curvature access through the generalized Gauss-Newton's low-rank structure","created":"2021-06-04","cited_by_count":16},{"id":"2101.08521","title":"Out-of-Distribution Generalization Analysis via Influence Function","created":"2021-01-21","cited_by_count":11},{"id":"1905.09201","title":"Adaptive norms for deep learning with regularized Newton methods","created":"2019-05-22","cited_by_count":5}],"next_cursor":null}