{"list":"other","total":67,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1412.6572","title":"Explaining and Harnessing Adversarial Examples","created":"2014-12-20","cited_by_count":7364},{"id":"1706.06083","title":"Towards Deep Learning Models Resistant to Adversarial Attacks","created":"2017-06-19","cited_by_count":6415},{"id":"2106.01946","title":"Convex optimization","created":"2021-06-03","cited_by_count":2515},{"id":"1306.0895","title":"Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distances","created":"2013-06-04","cited_by_count":2316},{"id":"1602.02697","title":"Practical Black-Box Attacks against Machine Learning","created":"2016-02-08","cited_by_count":903},{"id":"1705.07204","title":"Ensemble Adversarial Training: Attacks and Defenses","created":"2017-05-19","cited_by_count":840},{"id":"1511.07528","title":"The Limitations of Deep Learning in Adversarial Settings","created":"2015-11-24","cited_by_count":790},{"id":"1803.00567","title":"Computational Optimal Transport","created":"2018-03-01","cited_by_count":780},{"id":"1511.04508","title":"Distillation as a Defense to Adversarial Perturbations against Deep Neural Networks","created":"2015-11-14","cited_by_count":678},{"id":"1507.00504","title":"Optimal Transport for Domain Adaptation","created":"2015-07-02","cited_by_count":463},{"id":"1706.00292","title":"Learning Generative Models with Sinkhorn Divergences","created":"2017-06-01","cited_by_count":314},{"id":"1505.05116","title":"Data-driven Distributionally Robust Optimization Using the Wasserstein Metric: Performance Guarantees and Tractable Reformulations","created":"2015-05-19","cited_by_count":291},{"id":"1705.08848","title":"Joint Distribution Optimal Transportation for Domain Adaptation","created":"2017-05-24","cited_by_count":282},{"id":"1705.09634","title":"Near-linear time approximation algorithms for optimal transport via Sinkhorn iteration","created":"2017-05-26","cited_by_count":223},{"id":"1605.08527","title":"Stochastic Optimization for Large-scale Optimal Transport","created":"2016-05-27","cited_by_count":189},{"id":"1604.02199","title":"Distributionally Robust Stochastic Optimization with Wasserstein Distance","created":"2016-04-08","cited_by_count":185},{"id":"1610.03425","title":"Statistics of Robust Optimization: A Generalized Empirical Likelihood Approach","created":"2016-10-11","cited_by_count":183},{"id":"2010.05893","title":"Large-Scale Methods for Distributionally Robust Optimization","created":"2020-10-12","cited_by_count":179},{"id":"1908.08729","title":"Wasserstein Distributionally Robust Optimization: Theory and Applications in Machine Learning","created":"2019-08-23","cited_by_count":170},{"id":"2003.12862","title":"Adversarial Robustness: From Self-Supervised Pre-Training to Fine-Tuning","created":"2020-03-28","cited_by_count":153},{"id":"1308.6594","title":"Mini-batch Stochastic Approximation Methods for Nonconvex Stochastic Composite Optimization","created":"2013-08-29","cited_by_count":143},{"id":"1402.5481","title":"From Predictive to Prescriptive Analytics","created":"2014-02-22","cited_by_count":143},{"id":"1712.07897","title":"Non-convex Optimization for Machine Learning","created":"2017-12-21","cited_by_count":133},{"id":"1509.09259","title":"Distributionally Robust Logistic Regression","created":"2015-09-30","cited_by_count":126},{"id":"1411.3803","title":"Stochastic Compositional Gradient Descent: Algorithms for Minimizing Compositions of Expected-Value Functions","created":"2014-11-14","cited_by_count":95},{"id":"1710.10016","title":"Regularization via Mass Transportation","created":"2017-10-27","cited_by_count":81},{"id":"1905.10943","title":"Distributionally Robust Optimization and Generalization in Kernel Methods","created":"2019-05-27","cited_by_count":73},{"id":"1709.08894","title":"On the regularization of Wasserstein GANs","created":"2017-09-26","cited_by_count":65},{"id":"1805.11897","title":"Differential Properties of Sinkhorn Approximation for Learning with Wasserstein Distance","created":"2018-05-30","cited_by_count":56},{"id":"1907.13196","title":"Wasserstein Robust Reinforcement Learning","created":"2019-07-30","cited_by_count":54},{"id":"1812.01094","title":"A Single Time-Scale Stochastic Approximation Method for Nested Stochastic Optimization","created":"2018-12-03","cited_by_count":53},{"id":"2009.04382","title":"Finite-Sample Guarantees for Wasserstein Distributionally Robust Optimization: Breaking the Curse of Dimensionality","created":"2020-09-09","cited_by_count":49},{"id":"2002.10790","title":"Biased Stochastic First-Order Methods for Conditional Stochastic Optimization and Applications in Meta Learning","created":"2020-02-25","cited_by_count":47},{"id":"2006.07458","title":"Projection Robust Wasserstein Distance and Riemannian Optimization","created":"2020-06-12","cited_by_count":45},{"id":"2007.09530","title":"A Distributionally Robust Approach to Fair Classification","created":"2020-07-18","cited_by_count":43},{"id":"1902.08708","title":"Distributionally Robust Reinforcement Learning","created":"2019-02-23","cited_by_count":42},{"id":"2003.02894","title":"Distributional Robustness and Regularization in Reinforcement Learning","created":"2020-03-05","cited_by_count":40},{"id":"1606.05225","title":"Geometric Median in Nearly Linear Time","created":"2016-06-16","cited_by_count":39},{"id":"1906.01437","title":"On the Efficiency of Entropic Regularized Algorithms for Optimal Transport","created":"2019-06-01","cited_by_count":35},{"id":"1810.02403","title":"Optimal Transport Based Distributionally Robust Optimization: Structural Properties and Iterative Schemes","created":"2018-10-04","cited_by_count":30},{"id":"1812.09808","title":"Wasserstein Distributionally Robust Stochastic Control: A Data-Driven Approach","created":"2018-12-24","cited_by_count":29},{"id":"2012.05199","title":"A Riemannian Block Coordinate Descent Method for Computing the Projection Robust Wasserstein Distance","created":"2020-12-09","cited_by_count":27},{"id":"2108.02120","title":"Statistical Analysis of Wasserstein Distributionally Robust Estimators","created":"2021-08-04","cited_by_count":27},{"id":"1802.04885","title":"Distributionally Robust Mean-Variance Portfolio Selection with Wasserstein Distances","created":"2018-02-13","cited_by_count":25},{"id":"1801.03600","title":"Multi-Level Stochastic Gradient Methods for Nested Composition Optimization","created":"2018-01-11","cited_by_count":24},{"id":"1906.01614","title":"Confidence Regions in Wasserstein Distributionally Robust Estimation","created":"2019-06-04","cited_by_count":24},{"id":"1803.07033","title":"Natural gradient via optimal transport","created":"2018-03-16","cited_by_count":20},{"id":"1905.11957","title":"Sample Complexity of Sample Average Approximation for Conditional Stochastic Optimization","created":"2019-05-28","cited_by_count":19},{"id":"2104.13326","title":"Fast Distributionally Robust Learning with Variance Reduced Min-Max Optimization","created":"2021-04-27","cited_by_count":19},{"id":"2010.11970","title":"Two-sample Test using Projected Wasserstein Distance","created":"2020-10-22","cited_by_count":17},{"id":"1806.07418","title":"On Distributionally Robust Chance Constrained Programs with Wasserstein Distance","created":"2018-06-19","cited_by_count":15},{"id":"1307.6279","title":"Likelihood Robust Optimization for Data-driven Problems","created":"2013-07-24","cited_by_count":13},{"id":"1702.08848","title":"Semi-supervised Learning based on Distributionally Robust Optimization","created":"2017-02-28","cited_by_count":12},{"id":"2103.16451","title":"Robustifying Conditional Portfolio Decisions via Optimal Transport","created":"2021-03-30","cited_by_count":12},{"id":"1809.00210","title":"Data-Driven Chance Constrained Programs over Wasserstein Balls","created":"2018-09-01","cited_by_count":9},{"id":"2011.04102","title":"Reliable Off-policy Evaluation for Reinforcement Learning","created":"2020-11-08","cited_by_count":9},{"id":"1612.00138","title":"Towards Robust Deep Neural Networks with BANG","created":"2016-12-01","cited_by_count":8},{"id":"2008.10249","title":"Information Constrained Optimal Transport: From Talagrand, to Marton, to Cover","created":"2020-08-24","cited_by_count":8},{"id":"2007.04458","title":"Robust Bayesian Classification Using an Optimistic Score Ratio","created":"2020-07-08","cited_by_count":7},{"id":"1811.00304","title":"Robust risk aggregation with neural networks","created":"2018-11-01","cited_by_count":6},{"id":"1711.04839","title":"Cooperative data-driven distributionally robust optimization","created":"2017-11-13","cited_by_count":5},{"id":"1910.12778","title":"A First-Order Algorithmic Framework for Wasserstein Distributionally Robust Logistic Regression","created":"2019-10-28","cited_by_count":5},{"id":"1701.04200","title":"Distributionally Robust Stochastic Optimization with Dependence Structure","created":"2017-01-16","cited_by_count":4},{"id":"2101.02498","title":"Mathematical Foundations of Distributionally Robust Multistage Optimization","created":"2021-01-07","cited_by_count":3},{"id":"1712.08015","title":"Risk-Based Distributionally Robust Optimal Power Flow With Dynamic Line Rating","created":"2017-12-21","cited_by_count":2},{"id":"2010.05398","title":"Tight Bounds for a Class of Data-Driven Distributionally Robust Risk Measures","created":"2020-10-12","cited_by_count":1}],"next_cursor":null}