{"list":"other","total":83,"rows":[{"id":"1601.00670","title":"Variational Inference: A Review for Statisticians","created":"2016-01-04","cited_by_count":1472},{"id":"2010.01412","title":"Sharpness-Aware Minimization for Efficiently Improving Generalization","created":"2020-10-03","cited_by_count":1417},{"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":"1912.13213","title":"Online Learning: A Modern Introduction Using Convex Optimization","created":"2019-12-31","cited_by_count":417},{"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":"1705.07809","title":"Information-theoretic analysis of generalization capability of learning algorithms","created":"2017-05-22","cited_by_count":303},{"id":"1306.6430","title":"A General Framework for Updating Belief Distributions","created":"2013-06-27","cited_by_count":175},{"id":"2001.09122","title":"Reasoning About Generalization via Conditional Mutual Information","created":"2020-01-24","cited_by_count":147},{"id":"1901.05353","title":"A Primer on PAC-Bayesian Learning","created":"2019-01-16","cited_by_count":132},{"id":"1804.05862","title":"Non-Vacuous Generalization Bounds at the ImageNet Scale: A PAC-Bayesian Compression Approach","created":"2018-04-16","cited_by_count":126},{"id":"1506.04091","title":"On the properties of variational approximations of Gibbs posteriors","created":"2015-06-12","cited_by_count":121},{"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":"2107.04562","title":"The Bayesian Learning Rule","created":"2021-07-09","cited_by_count":99},{"id":"1412.3730","title":"Inconsistency of Bayesian Inference for Misspecified Linear Models, and a Proposal for Repairing It","created":"2014-12-11","cited_by_count":95},{"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":"1605.08636","title":"PAC-Bayesian Theory Meets Bayesian Inference","created":"2016-05-27","cited_by_count":88},{"id":"2002.05551","title":"PACOH: Bayes-Optimal Meta-Learning with PAC-Guarantees","created":"2020-02-13","cited_by_count":85},{"id":"2102.00931","title":"Information-Theoretic Generalization Bounds for Stochastic Gradient Descent","created":"2021-02-01","cited_by_count":84},{"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":"1711.01244","title":"Meta-Learning by Adjusting Priors Based on Extended PAC-Bayes Theory","created":"2017-11-03","cited_by_count":76},{"id":"1311.2838","title":"A PAC-Bayesian bound for Lifelong Learning","created":"2013-11-12","cited_by_count":69},{"id":"1706.09293","title":"Concentration of tempered posteriors and of their variational approximations","created":"2017-06-28","cited_by_count":66},{"id":"1806.03803","title":"Chaining Mutual Information and Tightening Generalization Bounds","created":"2018-06-11","cited_by_count":65},{"id":"2006.13057","title":"PAC-Bayes Analysis Beyond the Usual Bounds","created":"2020-06-23","cited_by_count":63},{"id":"1901.04653","title":"Normalized Flat Minima: Exploring Scale Invariant Definition of Flat Minima for Neural Networks using PAC-Bayesian Analysis","created":"2019-01-15","cited_by_count":59},{"id":"1608.05610","title":"A Strongly Quasiconvex PAC-Bayesian Bound","created":"2016-08-19","cited_by_count":54},{"id":"1503.08329","title":"Risk Bounds for the Majority Vote: From a PAC-Bayesian Analysis to a Learning Algorithm","created":"2015-03-28","cited_by_count":50},{"id":"1610.07193","title":"Simpler PAC-Bayesian Bounds for Hostile Data","created":"2016-10-23","cited_by_count":46},{"id":"1712.02519","title":"Convergence Rates of Variational Posterior Distributions","created":"2017-12-07","cited_by_count":45},{"id":"1307.2118","title":"A PAC-Bayesian Tutorial with A Dropout Bound","created":"2013-07-08","cited_by_count":43},{"id":"2005.08044","title":"Generalization Bounds via Information Density and Conditional Information Density","created":"2020-05-16","cited_by_count":43},{"id":"2006.07279","title":"PAC-Bayes unleashed: generalisation bounds with unbounded losses","created":"2020-06-12","cited_by_count":43},{"id":"2101.09315","title":"Tighter expected generalization error bounds via Wasserstein distance","created":"2021-01-22","cited_by_count":43},{"id":"1905.10259","title":"Dichotomize and Generalize: PAC-Bayesian Binary Activated Deep Neural Networks","created":"2019-05-24","cited_by_count":38},{"id":"1905.13367","title":"PAC-Bayes Un-Expected Bernstein Inequality","created":"2019-05-31","cited_by_count":36},{"id":"1908.07380","title":"PAC-Bayes with Backprop","created":"2019-08-19","cited_by_count":36},{"id":"1802.07543","title":"The Many Faces of Exponential Weights in Online Learning","created":"2018-02-21","cited_by_count":33},{"id":"2106.09683","title":"PAC-Bayes, MAC-Bayes and Conditional Mutual Information: Fast rate bounds that handle general VC classes","created":"2021-06-17","cited_by_count":31},{"id":"1506.04573","title":"A New PAC-Bayesian Perspective on Domain Adaptation","created":"2015-06-15","cited_by_count":29},{"id":"1709.06617","title":"A PAC-Bayesian Analysis of Randomized Learning with Application to Stochastic Gradient Descent","created":"2017-09-19","cited_by_count":29},{"id":"2006.12228","title":"Differentiable PAC-Bayes Objectives with Partially Aggregated Neural Networks","created":"2020-06-22","cited_by_count":29},{"id":"2109.14509","title":"PAC-Bayes Information Bottleneck","created":"2021-09-29","cited_by_count":28},{"id":"1509.00922","title":"Calibrating general posterior credible regions","created":"2015-09-03","cited_by_count":27},{"id":"1605.00252","title":"Fast Rates for General Unbounded Loss Functions: from ERM to Generalized Bayes","created":"2016-05-01","cited_by_count":27},{"id":"1908.04847","title":"Convergence Rates of Variational Inference in Sparse Deep Learning","created":"2019-08-09","cited_by_count":27},{"id":"2006.13508","title":"A Limitation of the PAC-Bayes Framework","created":"2020-06-24","cited_by_count":25},{"id":"2106.03542","title":"How Tight Can PAC-Bayes be in the Small Data Regime?","created":"2021-06-07","cited_by_count":24},{"id":"1905.12654","title":"On the Generalization Gap in Reparameterizable Reinforcement Learning","created":"2019-05-29","cited_by_count":22},{"id":"2010.09541","title":"On the Difficulty of Unbiased Alpha Divergence Minimization","created":"2020-10-19","cited_by_count":21},{"id":"1908.07585","title":"Fast-rate PAC-Bayes Generalization Bounds via Shifted Rademacher Processes","created":"2019-08-20","cited_by_count":20},{"id":"1910.04464","title":"PAC-Bayesian Contrastive Unsupervised Representation Learning","created":"2019-10-10","cited_by_count":20},{"id":"2107.03955","title":"On Margins and Derandomisation in PAC-Bayes","created":"2021-07-08","cited_by_count":19},{"id":"1805.05054","title":"Consistency of Variational Bayes Inference for Estimation and Model Selection in Mixtures","created":"2018-05-14","cited_by_count":17},{"id":"1904.03920","title":"A Generalization Bound for Online Variational Inference","created":"2019-04-08","cited_by_count":17},{"id":"2109.03204","title":"Adaptive variational Bayes: Optimality, computation and applications","created":"2021-09-07","cited_by_count":17},{"id":"1905.07900","title":"PAC-Bayes under potentially heavy tails","created":"2019-05-20","cited_by_count":16},{"id":"2006.09914","title":"Learning Partially Known Stochastic Dynamics with Empirical PAC Bayes","created":"2020-06-17","cited_by_count":16},{"id":"2104.08324","title":"On the Robustness to Misspecification of $\\alpha$-Posteriors and Their Variational Approximations","created":"2021-04-16","cited_by_count":15},{"id":"2007.05824","title":"Generalization bound of globally optimal non-convex neural network training: Transportation map estimation by infinite dimensional Langevin dynamics","created":"2020-07-11","cited_by_count":14},{"id":"2011.02872","title":"Transfer Meta-Learning: Information-Theoretic Bounds and Information Meta-Risk Minimization","created":"2020-11-04","cited_by_count":14},{"id":"2105.01747","title":"Information Complexity and Generalization Bounds","created":"2021-05-04","cited_by_count":14},{"id":"1809.09505","title":"Practical bounds on the error of Bayesian posterior approximations: A nonasymptotic approach","created":"2018-09-25","cited_by_count":12},{"id":"1604.04191","title":"1-bit Matrix Completion: PAC-Bayesian Analysis of a Variational Approximation","created":"2016-04-14","cited_by_count":11},{"id":"2102.03748","title":"PAC-Bayes Bounds for Meta-learning with Data-Dependent Prior","created":"2021-02-07","cited_by_count":11},{"id":"2106.09798","title":"Wide stochastic networks: Gaussian limit and PAC-Bayesian training","created":"2021-06-17","cited_by_count":10},{"id":"1306.3862","title":"Bayesian methods for low-rank matrix estimation: short survey and theoretical study","created":"2013-06-17","cited_by_count":7},{"id":"2103.12866","title":"PAC-Bayesian theory for stochastic LTI systems","created":"2021-03-23","cited_by_count":7},{"id":"1804.05474","title":"A Direct Sum Result for the Information Complexity of Learning","created":"2018-04-16","cited_by_count":6},{"id":"1909.03009","title":"Dissecting Non-Vacuous Generalization Bounds based on the Mean-Field Approximation","created":"2019-09-06","cited_by_count":6},{"id":"2102.02504","title":"Meta-strategy for Learning Tuning Parameters with Guarantees","created":"2021-02-04","cited_by_count":6},{"id":"1410.1771","title":"PAC-Bayesian AUC classification and scoring","created":"2014-10-07","cited_by_count":5},{"id":"2012.04505","title":"Gibbs posterior concentration rates under sub-exponential type losses","created":"2020-12-08","cited_by_count":5},{"id":"1311.2799","title":"Aggregation of Affine Estimators","created":"2013-11-12","cited_by_count":4},{"id":"1405.1580","title":"PAC-Bayes Mini-tutorial: A Continuous Union Bound","created":"2014-05-07","cited_by_count":4},{"id":"1902.01902","title":"Asymptotic Consistency of $\\alpha-$R\\'enyi-Approximate Posteriors","created":"2019-02-05","cited_by_count":4},{"id":"2104.14054","title":"Loss-Based Variational Bayes Prediction","created":"2021-04-29","cited_by_count":4},{"id":"1611.08483","title":"On the Exponentially Weighted Aggregate with the Laplace Prior","created":"2016-11-25","cited_by_count":3},{"id":"2012.10369","title":"Upper and Lower Bounds on the Performance of Kernel PCA","created":"2020-12-18","cited_by_count":3},{"id":"2107.13656","title":"Characterizing the Generalization Error of Gibbs Algorithm with Symmetrized KL information","created":"2021-07-28","cited_by_count":3},{"id":"1902.04247","title":"PAC-Bayes Analysis of Sentence Representation","created":"2019-02-12","cited_by_count":2},{"id":"2006.08888","title":"PAC-Bayesian Generalization Bounds for MultiLayer Perceptrons","created":"2020-06-16","cited_by_count":2}],"next_cursor":null}