{"list":"other","total":78,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"1710.09412","title":"mixup: Beyond Empirical Risk Minimization","created":"2017-10-25","cited_by_count":5183},{"id":"1810.00826","title":"How Powerful are Graph Neural Networks?","created":"2018-10-01","cited_by_count":4393},{"id":"1704.01212","title":"Neural Message Passing for Quantum Chemistry","created":"2017-04-04","cited_by_count":3487},{"id":"2005.00687","title":"Open Graph Benchmark: Datasets for Machine Learning on Graphs","created":"2020-05-02","cited_by_count":2163},{"id":"1908.09635","title":"A Survey on Bias and Fairness in Machine Learning","created":"2019-08-23","cited_by_count":1917},{"id":"1901.07031","title":"CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparison","created":"2019-01-21","cited_by_count":1423},{"id":"2012.07421","title":"WILDS: A Benchmark of in-the-Wild Distribution Shifts","created":"2020-12-14","cited_by_count":1375},{"id":"1703.00564","title":"MoleculeNet: A Benchmark for Molecular Machine Learning","created":"2017-03-02","cited_by_count":1051},{"id":"1905.12265","title":"Strategies for Pre-training Graph Neural Networks","created":"2019-05-29","cited_by_count":971},{"id":"1909.05207","title":"Introduction to Online Convex Optimization","created":"2019-09-07","cited_by_count":803},{"id":"1806.10574","title":"This Looks Like That: Deep Learning for Interpretable Image Recognition","created":"2018-06-27","cited_by_count":737},{"id":"2010.00747","title":"Contrastive Learning of Medical Visual Representations from Paired Images and Text","created":"2020-10-02","cited_by_count":641},{"id":"1806.03962","title":"Rotation Equivariant CNNs for Digital Pathology","created":"2018-06-08","cited_by_count":422},{"id":"1912.13213","title":"Online Learning: A Modern Introduction Using Convex Optimization","created":"2019-12-31","cited_by_count":417},{"id":"1903.04561","title":"Nuanced Metrics for Measuring Unintended Bias with Real Data for Text Classification","created":"2019-03-11","cited_by_count":404},{"id":"2010.04053","title":"Fairness in Machine Learning: A Survey","created":"2020-10-04","cited_by_count":370},{"id":"2101.05224","title":"Big Self-Supervised Models Advance Medical Image Classification","created":"2021-01-13","cited_by_count":320},{"id":"1810.01943","title":"AI Fairness 360: An Extensible Toolkit for Detecting, Understanding, and Mitigating Unwanted Algorithmic Bias","created":"2018-10-03","cited_by_count":319},{"id":"1905.10018","title":"Momentum-Based Variance Reduction in Non-Convex SGD","created":"2019-05-24","cited_by_count":306},{"id":"1807.01695","title":"SPIDER: Near-Optimal Non-Convex Optimization via Stochastic Path Integrated Differential Estimator","created":"2018-07-04","cited_by_count":287},{"id":"1906.00331","title":"On Gradient Descent Ascent for Nonconvex-Concave Minimax Problems","created":"2019-06-02","cited_by_count":270},{"id":"1703.00102","title":"SARAH: A Novel Method for Machine Learning Problems Using Stochastic Recursive Gradient","created":"2017-03-01","cited_by_count":220},{"id":"1803.06523","title":"Stochastic model-based minimization of weakly convex functions","created":"2018-03-17","cited_by_count":159},{"id":"2003.00827","title":"CheXclusion: Fairness gaps in deep chest X-ray classifiers","created":"2020-02-14","cited_by_count":153},{"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":"1910.07833","title":"Sharper bounds for uniformly stable algorithms","created":"2019-10-17","cited_by_count":93},{"id":"1709.01953","title":"Implicit Regularization in Deep Learning","created":"2017-09-06","cited_by_count":90},{"id":"2106.03721","title":"OoD-Bench: Quantifying and Understanding Two Dimensions of Out-of-Distribution Generalization","created":"2021-06-07","cited_by_count":86},{"id":"2001.03724","title":"Stochastic Recursive Gradient Descent Ascent for Stochastic Nonconvex-Strongly-Concave Minimax Problems","created":"2020-01-11","cited_by_count":77},{"id":"1906.10651","title":"Interpretable Image Recognition with Hierarchical Prototypes","created":"2019-06-25","cited_by_count":65},{"id":"1810.02060","title":"Weakly-Convex Concave Min-Max Optimization: Provable Algorithms and Applications in Machine Learning","created":"2018-10-04","cited_by_count":63},{"id":"1908.10831","title":"Stochastic AUC Maximization with Deep Neural Networks","created":"2019-08-28","cited_by_count":61},{"id":"1605.06398","title":"Stochastic Variance Reduction Methods for Saddle-Point Problems","created":"2016-05-20","cited_by_count":60},{"id":"1812.09859","title":"Generalization Bounds for Uniformly Stable Algorithms","created":"2018-12-24","cited_by_count":56},{"id":"1804.06500","title":"Two-Player Games for Efficient Non-Convex Constrained Optimization","created":"2018-04-17","cited_by_count":55},{"id":"1812.01094","title":"A Single Time-Scale Stochastic Approximation Method for Nested Stochastic Optimization","created":"2018-12-03","cited_by_count":53},{"id":"1901.09314","title":"On Symmetric Losses for Learning from Corrupted Labels","created":"2019-01-27","cited_by_count":53},{"id":"2112.05604","title":"Faster Single-loop Algorithms for Minimax Optimization without Strong Concavity","created":"2021-12-10","cited_by_count":49},{"id":"2012.01981","title":"Advanced Graph and Sequence Neural Networks for Molecular Property Prediction and Drug Discovery","created":"2020-12-02","cited_by_count":46},{"id":"1305.1363","title":"One-Pass AUC Optimization","created":"2013-05-07","cited_by_count":42},{"id":"1608.04802","title":"Scalable Learning of Non-Decomposable Objectives","created":"2016-08-16","cited_by_count":41},{"id":"1902.05826","title":"The Fairness of Risk Scores Beyond Classification: Bipartite Ranking and the xAUC Metric","created":"2019-02-15","cited_by_count":41},{"id":"2101.07563","title":"Using StyleGAN for Visual Interpretability of Deep Learning Models on Medical Images","created":"2021-01-19","cited_by_count":35},{"id":"2107.13171","title":"Learning with Multiclass AUC: Theory and Algorithms","created":"2021-07-28","cited_by_count":35},{"id":"1409.3257","title":"Stochastic Primal-Dual Coordinate Method for Regularized Empirical Risk Minimization","created":"2014-09-10","cited_by_count":31},{"id":"2203.00176","title":"When AUC meets DRO: Optimizing Partial AUC for Deep Learning with Non-Convex Convergence Guarantee","created":"2022-03-01","cited_by_count":29},{"id":"2005.02426","title":"Communication-Efficient Distributed Stochastic AUC Maximization with Deep Neural Networks","created":"2020-05-05","cited_by_count":27},{"id":"2007.13605","title":"Alternating proximal-gradient steps for (stochastic) nonconvex-concave minimax problems","created":"2020-07-27","cited_by_count":26},{"id":"1305.2505","title":"On the Generalization Ability of Online Learning Algorithms for Pairwise Loss Functions","created":"2013-05-11","cited_by_count":23},{"id":"1410.6776","title":"Online and Stochastic Gradient Methods for Non-decomposable Loss Functions","created":"2014-10-24","cited_by_count":21},{"id":"2102.04635","title":"Federated Deep AUC Maximization for Heterogeneous Data with a Constant Communication Complexity","created":"2021-02-09","cited_by_count":21},{"id":"1705.01708","title":"Semi-Supervised AUC Optimization based on Positive-Unlabeled Learning","created":"2017-05-04","cited_by_count":20},{"id":"2102.06764","title":"Technical Challenges for Training Fair Neural Networks","created":"2021-02-12","cited_by_count":20},{"id":"2111.12050","title":"Simple Stochastic and Online Gradient Descent Algorithms for Pairwise Learning","created":"2021-11-23","cited_by_count":20},{"id":"2006.06889","title":"Fast Objective & Duality Gap Convergence for Non-Convex Strongly-Concave Min-Max Problems with PL Condition","created":"2020-06-12","cited_by_count":19},{"id":"1904.10112","title":"Stochastic Primal-Dual Algorithms with Faster Convergence than $O(1/\\sqrt{T})$ for Problems without Bilinear Structure","created":"2019-04-23","cited_by_count":15},{"id":"2203.01505","title":"Large-scale Optimization of Partial AUC in a Range of False Positive Rates","created":"2022-03-03","cited_by_count":15},{"id":"1906.06053","title":"Stochastic Proximal AUC Maximization","created":"2019-06-14","cited_by_count":14},{"id":"2003.04375","title":"A Primal-Dual Smoothing Framework for Max-Structured Non-Convex Optimization","created":"2020-03-09","cited_by_count":14},{"id":"1605.04337","title":"Support Vector Algorithms for Optimizing the Partial Area Under the ROC Curve","created":"2016-05-13","cited_by_count":12},{"id":"1508.00298","title":"Two-Way Partial AUC and Its Properties","created":"2015-08-03","cited_by_count":11},{"id":"2005.11074","title":"An Introduction to Neural Architecture Search for Convolutional Networks","created":"2020-05-22","cited_by_count":10},{"id":"2203.14177","title":"Benchmarking Deep AUROC Optimization: Loss Functions and Algorithmic Choices","created":"2022-03-27","cited_by_count":10},{"id":"1410.1462","title":"Top Rank Optimization in Linear Time","created":"2014-10-06","cited_by_count":9},{"id":"2107.10960","title":"Implicit Rate-Constrained Optimization of Non-decomposable Objectives","created":"2021-07-23","cited_by_count":9},{"id":"1803.06604","title":"A Robust AUC Maximization Framework with Simultaneous Outlier Detection and Feature Selection for Positive-Unlabeled Classification","created":"2018-03-18","cited_by_count":5},{"id":"1806.04838","title":"Partial AUC Maximization via Nonlinear Scoring Functions","created":"2018-06-13","cited_by_count":5},{"id":"2112.08363","title":"Performance or Trust? Why Not Both. Deep AUC Maximization with Self-Supervised Learning for COVID-19 Chest X-ray Classifications","created":"2021-12-14","cited_by_count":4},{"id":"1301.5332","title":"Online Learning with Pairwise Loss Functions","created":"2013-01-22","cited_by_count":3},{"id":"1912.11193","title":"Quadruply Stochastic Gradient Method for Large Scale Nonlinear Semi-Supervised Ordinal Regression AUC Optimization","created":"2019-12-24","cited_by_count":3},{"id":"2009.10867","title":"Online AUC Optimization for Sparse High-Dimensional Datasets","created":"2020-09-23","cited_by_count":3},{"id":"1310.0900","title":"Efficient pedestrian detection by directly optimize the partial area under the ROC curve","created":"2013-10-03","cited_by_count":2},{"id":"2011.02396","title":"Stochastic Hard Thresholding Algorithms for AUC Maximization","created":"2020-11-04","cited_by_count":2},{"id":"1911.03548","title":"Variance Reduced Stochastic Proximal Algorithm for AUC Maximization","created":"2019-11-08","cited_by_count":1}],"next_cursor":null}