{"list":"other","total":69,"rows":[{"id":"1505.07818","title":"Domain-Adversarial Training of Neural Networks","created":"2015-05-28","cited_by_count":3044},{"id":"1903.12261","title":"Benchmarking Neural Network Robustness to Common Corruptions and Perturbations","created":"2019-03-28","cited_by_count":2877},{"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":"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":"1812.01754","title":"Moment Matching for Multi-Source Domain Adaptation","created":"2018-12-04","cited_by_count":1331},{"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":"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":"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":"1509.01240","title":"Train faster, generalize better: Stability of stochastic gradient descent","created":"2015-09-03","cited_by_count":552},{"id":"2011.03395","title":"Underspecification Presents Challenges for Credibility in Modern Machine Learning","created":"2020-11-06","cited_by_count":496},{"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":"1705.07809","title":"Information-theoretic analysis of generalization capability of learning algorithms","created":"2017-05-22","cited_by_count":303},{"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":"1805.12177","title":"Why do deep convolutional networks generalize so poorly to small image transformations?","created":"2018-05-30","cited_by_count":198},{"id":"2002.07017","title":"Learning Robust Representations via Multi-View Information Bottleneck","created":"2020-02-17","cited_by_count":191},{"id":"2104.09841","title":"SelfReg: Self-supervised Contrastive Regularization for Domain Generalization","created":"2021-04-20","cited_by_count":189},{"id":"2109.02934","title":"Fishr: Invariant Gradient Variances for Out-of-Distribution Generalization","created":"2021-09-07","cited_by_count":186},{"id":"2001.00677","title":"Improve Unsupervised Domain Adaptation with Mixup Training","created":"2020-01-03","cited_by_count":185},{"id":"2007.02931","title":"Adaptive Risk Minimization: Learning to Adapt to Domain Shift","created":"2020-07-06","cited_by_count":183},{"id":"1711.07910","title":"Domain Generalization by Marginal Transfer Learning","created":"2017-11-21","cited_by_count":180},{"id":"2006.06914","title":"Stability of Stochastic Gradient Descent on Nonsmooth Convex Losses","created":"2020-06-12","cited_by_count":173},{"id":"2010.15775","title":"Understanding the Failure Modes of Out-of-Distribution Generalization","created":"2020-10-29","cited_by_count":146},{"id":"2009.00329","title":"Learning explanations that are hard to vary","created":"2020-09-01","cited_by_count":132},{"id":"1911.02151","title":"Information-Theoretic Generalization Bounds for SGLD via Data-Dependent Estimates","created":"2019-11-06","cited_by_count":119},{"id":"1901.04609","title":"Tightening Mutual Information Based Bounds on Generalization Error","created":"2019-01-15","cited_by_count":117},{"id":"2101.01134","title":"Does Invariant Risk Minimization Capture Invariance?","created":"2021-01-04","cited_by_count":116},{"id":"1511.05219","title":"How much does your data exploration overfit? Controlling bias via information usage","created":"2015-11-16","cited_by_count":95},{"id":"2102.00931","title":"Information-Theoretic Generalization Bounds for Stochastic Gradient Descent","created":"2021-02-01","cited_by_count":84},{"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":"1801.04295","title":"Generalization Error Bounds for Noisy, Iterative Algorithms","created":"2018-01-12","cited_by_count":82},{"id":"2002.05379","title":"The Conditional Entropy Bottleneck","created":"2020-02-13","cited_by_count":75},{"id":"2010.04647","title":"Learning Invariant Representations and Risks for Semi-supervised Domain Adaptation","created":"2020-10-09","cited_by_count":69},{"id":"2006.07433","title":"A causal framework for distribution generalization","created":"2020-06-12","cited_by_count":68},{"id":"2207.09944","title":"Probable Domain Generalization via Quantile Risk Minimization","created":"2022-07-20","cited_by_count":66},{"id":"2309.04381","title":"Generalization Bounds: Perspectives from Information Theory and PAC-Bayes","created":"2023-09-08","cited_by_count":61},{"id":"2207.13887","title":"Adaptive Second Order Coresets for Data-efficient Machine Learning","created":"2022-07-28","cited_by_count":60},{"id":"2008.01883","title":"When is invariance useful in an Out-of-Distribution Generalization problem ?","created":"2020-08-04","cited_by_count":52},{"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":"2110.01584","title":"Information-theoretic generalization bounds for black-box learning algorithms","created":"2021-10-04","cited_by_count":49},{"id":"2109.14595","title":"Generalization Bounds For Meta-Learning: An Information-Theoretic Analysis","created":"2021-09-29","cited_by_count":45},{"id":"2101.09315","title":"Tighter expected generalization error bounds via Wasserstein distance","created":"2021-01-22","cited_by_count":43},{"id":"2109.12909","title":"Compressive Visual Representations","created":"2021-09-27","cited_by_count":41},{"id":"2206.07766","title":"Pareto Invariant Risk Minimization: Towards Mitigating the Optimization Dilemma in Out-of-Distribution Generalization","created":"2022-06-15","cited_by_count":38},{"id":"2105.03793","title":"Stability and Generalization of Stochastic Gradient Methods for Minimax Problems","created":"2021-05-08","cited_by_count":36},{"id":"2106.07780","title":"KL Guided Domain Adaptation","created":"2021-06-14","cited_by_count":35},{"id":"2005.04372","title":"Information-Theoretic Generalization Bounds for Meta-Learning and Applications","created":"2020-05-09","cited_by_count":32},{"id":"2110.03128","title":"On the Generalization of Models Trained with SGD: Information-Theoretic Bounds and Implications","created":"2021-10-07","cited_by_count":31},{"id":"2206.11646","title":"Invariant Causal Mechanisms through Distribution Matching","created":"2022-06-23","cited_by_count":31},{"id":"2210.06422","title":"A New Family of Generalization Bounds Using Samplewise Evaluated CMI","created":"2022-10-12","cited_by_count":28},{"id":"2106.03783","title":"An Information-theoretic Approach to Distribution Shifts","created":"2021-06-07","cited_by_count":25},{"id":"2302.02432","title":"Tighter Information-Theoretic Generalization Bounds from Supersamples","created":"2023-02-05","cited_by_count":22},{"id":"2111.12050","title":"Simple Stochastic and Online Gradient Descent Algorithms for Pairwise Learning","created":"2021-11-23","cited_by_count":20},{"id":"2206.05263","title":"Causal Balancing for Domain Generalization","created":"2022-06-10","cited_by_count":20},{"id":"2210.00706","title":"Information-Theoretic Analysis of Unsupervised Domain Adaptation","created":"2022-10-03","cited_by_count":15},{"id":"2211.06617","title":"Empirical Risk Minimization with Relative Entropy Regularization","created":"2022-11-12","cited_by_count":13},{"id":"2202.12150","title":"Tighter Expected Generalization Error Bounds via Convexity of Information Measures","created":"2022-02-24","cited_by_count":11},{"id":"2210.06511","title":"Evaluated CMI Bounds for Meta Learning: Tightness and Expressiveness","created":"2022-10-12","cited_by_count":11},{"id":"2302.02931","title":"Bitrate-Constrained DRO: Beyond Worst Case Robustness To Unknown Group Shifts","created":"2023-02-06","cited_by_count":9},{"id":"2305.01134","title":"PGrad: Learning Principal Gradients For Domain Generalization","created":"2023-05-02","cited_by_count":8},{"id":"2304.14332","title":"On the Generalization Error of Meta Learning for the Gibbs Algorithm","created":"2023-04-27","cited_by_count":2}],"next_cursor":null}