{"list":"other","total":53,"rows":[{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1609.04836","title":"On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima","created":"2016-09-15","cited_by_count":1352},{"id":"1612.00410","title":"Deep Variational Information Bottleneck","created":"2016-12-01","cited_by_count":930},{"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":"1707.09564","title":"A PAC-Bayesian Approach to Spectrally-Normalized Margin Bounds for Neural Networks","created":"2017-07-29","cited_by_count":314},{"id":"1802.05296","title":"Stronger generalization bounds for deep nets via a compression approach","created":"2018-02-14","cited_by_count":307},{"id":"1705.07809","title":"Information-theoretic analysis of generalization capability of learning algorithms","created":"2017-05-22","cited_by_count":303},{"id":"2110.11216","title":"User-friendly introduction to PAC-Bayes bounds","created":"2021-10-21","cited_by_count":239},{"id":"2001.09122","title":"Reasoning About Generalization via Conditional Mutual Information","created":"2020-01-24","cited_by_count":147},{"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":"2007.12911","title":"Tighter risk certificates for neural networks","created":"2020-07-25","cited_by_count":112},{"id":"2305.18887","title":"How Does Information Bottleneck Help Deep Learning?","created":"2023-05-30","cited_by_count":93},{"id":"2102.00931","title":"Information-Theoretic Generalization Bounds for Stochastic Gradient Descent","created":"2021-02-01","cited_by_count":84},{"id":"1506.02629","title":"Generalization in Adaptive Data Analysis and Holdout Reuse","created":"2015-06-08","cited_by_count":83},{"id":"1712.09376","title":"Entropy-SGD optimizes the prior of a PAC-Bayes bound: Generalization properties of Entropy-SGD and data-dependent priors","created":"2017-12-26","cited_by_count":81},{"id":"1711.08856","title":"Critical Learning Periods in Deep Neural Networks","created":"2017-11-24","cited_by_count":79},{"id":"2002.05379","title":"The Conditional Entropy Bottleneck","created":"2020-02-13","cited_by_count":75},{"id":"1705.02436","title":"Nonlinear Information Bottleneck","created":"2017-05-06","cited_by_count":71},{"id":"1802.09766","title":"Learning Representations for Neural Network-Based Classification Using the Information Bottleneck Principle","created":"2018-02-27","cited_by_count":70},{"id":"2111.13171","title":"Intrinsic Dimension, Persistent Homology and Generalization in Neural Networks","created":"2021-11-25","cited_by_count":70},{"id":"2006.13057","title":"PAC-Bayes Analysis Beyond the Usual Bounds","created":"2020-06-23","cited_by_count":63},{"id":"2006.09313","title":"Hausdorff Dimension, Heavy Tails, and Generalization in Neural Networks","created":"2020-06-16","cited_by_count":62},{"id":"1608.05610","title":"A Strongly Quasiconvex PAC-Bayesian Bound","created":"2016-08-19","cited_by_count":54},{"id":"2005.11818","title":"Proper Learning, Helly Number, and an Optimal SVM Bound","created":"2020-05-24","cited_by_count":53},{"id":"2110.01584","title":"Information-theoretic generalization bounds for black-box learning algorithms","created":"2021-10-04","cited_by_count":49},{"id":"1912.01439","title":"Generalization Error Bounds Via R\\'enyi-, $f$-Divergences and Maximal Leakage","created":"2019-12-01","cited_by_count":48},{"id":"1912.04265","title":"In Defense of Uniform Convergence: Generalization via derandomization with an application to interpolating predictors","created":"2019-12-09","cited_by_count":44},{"id":"2106.03795","title":"Heavy Tails in SGD and Compressibility of Overparametrized Neural Networks","created":"2021-06-07","cited_by_count":44},{"id":"2003.09671","title":"On Information Plane Analyses of Neural Network Classifiers -- A Review","created":"2020-03-21","cited_by_count":37},{"id":"1808.07593","title":"Caveats for information bottleneck in deterministic scenarios","created":"2018-08-23","cited_by_count":34},{"id":"2104.05641","title":"Generalization bounds via distillation","created":"2021-04-12","cited_by_count":34},{"id":"1906.09855","title":"Universal Bayes consistency in metric spaces","created":"2019-06-24","cited_by_count":33},{"id":"2009.12789","title":"Learning Optimal Representations with the Decodable Information Bottleneck","created":"2020-09-27","cited_by_count":33},{"id":"1807.04193","title":"Distributed Variational Representation Learning","created":"2018-07-11","cited_by_count":32},{"id":"2011.04586","title":"Stable Sample Compression Schemes: New Applications and an Optimal SVM Margin Bound","created":"2020-11-09","cited_by_count":32},{"id":"2012.09922","title":"Individually Conditional Individual Mutual Information Bound on Generalization Error","created":"2020-12-17","cited_by_count":30},{"id":"2111.05275","title":"Towards a Unified Information-Theoretic Framework for Generalization","created":"2021-11-09","cited_by_count":30},{"id":"2110.08678","title":"Improving Transformers with Probabilistic Attention Keys","created":"2021-10-16","cited_by_count":28},{"id":"2210.06422","title":"A New Family of Generalization Bounds Using Samplewise Evaluated CMI","created":"2022-10-12","cited_by_count":28},{"id":"2108.00781","title":"Generalization Bounds using Lower Tail Exponents in Stochastic Optimizers","created":"2021-08-02","cited_by_count":27},{"id":"2202.04985","title":"Generalization Bounds via Convex Analysis","created":"2022-02-10","cited_by_count":27},{"id":"2203.02474","title":"Rate-Distortion Theoretic Generalization Bounds for Stochastic Learning Algorithms","created":"2022-03-04","cited_by_count":22},{"id":"1805.08254","title":"Sample Compression for Real-Valued Learners","created":"2018-05-21","cited_by_count":19},{"id":"1807.11824","title":"t-SNE-CUDA: GPU-Accelerated t-SNE and its Applications to Modern Data","created":"2018-07-31","cited_by_count":19},{"id":"2212.13556","title":"Limitations of Information-Theoretic Generalization Bounds for Gradient Descent Methods in Stochastic Convex Optimization","created":"2022-12-27","cited_by_count":19},{"id":"2302.04925","title":"Information Theoretic Lower Bounds for Information Theoretic Upper Bounds","created":"2023-02-09","cited_by_count":17},{"id":"1911.11000","title":"The Convex Information Bottleneck Lagrangian","created":"2019-11-25","cited_by_count":16},{"id":"2205.12239","title":"Gacs-Korner Common Information Variational Autoencoder","created":"2022-05-24","cited_by_count":12},{"id":"2402.03254","title":"Minimum Description Length and Generalization Guarantees for Representation Learning","created":"2024-02-05","cited_by_count":11},{"id":"2205.11361","title":"Chaotic Regularization and Heavy-Tailed Limits for Deterministic Gradient Descent","created":"2022-05-23","cited_by_count":9},{"id":"2303.05369","title":"Data-dependent Generalization Bounds via Variable-Size Compressibility","created":"2023-03-09","cited_by_count":9},{"id":"2304.14618","title":"Recognizable Information Bottleneck","created":"2023-04-28","cited_by_count":5}],"next_cursor":null}