{"list":"other","total":86,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1602.05629","title":"Communication-Efficient Learning of Deep Networks from Decentralized Data","created":"2016-02-17","cited_by_count":7669},{"id":"1806.07366","title":"Neural Ordinary Differential Equations","created":"2018-06-19","cited_by_count":3779},{"id":"1310.4546","title":"Distributed Representations of Words and Phrases and their Compositionality","created":"2013-10-16","cited_by_count":3474},{"id":"1505.07818","title":"Domain-Adversarial Training of Neural Networks","created":"2015-05-28","cited_by_count":3044},{"id":"1306.0895","title":"Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distances","created":"2013-06-04","cited_by_count":2316},{"id":"1704.00028","title":"Improved Training of Wasserstein GANs","created":"2017-03-31","cited_by_count":2235},{"id":"1802.05957","title":"Spectral Normalization for Generative Adversarial Networks","created":"2018-02-16","cited_by_count":1636},{"id":"1601.00670","title":"Variational Inference: A Review for Statisticians","created":"2016-01-04","cited_by_count":1472},{"id":"1707.06887","title":"A Distributional Perspective on Reinforcement Learning","created":"2017-07-21","cited_by_count":765},{"id":"1702.08165","title":"Reinforcement Learning with Deep Energy-Based Policies","created":"2017-02-27","cited_by_count":669},{"id":"1802.03601","title":"Deep Visual Domain Adaptation: A Survey","created":"2018-02-10","cited_by_count":635},{"id":"1710.10044","title":"Distributional Reinforcement Learning with Quantile Regression","created":"2017-10-27","cited_by_count":474},{"id":"1507.00504","title":"Optimal Transport for Domain Adaptation","created":"2015-07-02","cited_by_count":463},{"id":"1609.07152","title":"Input Convex Neural Networks","created":"2016-09-22","cited_by_count":414},{"id":"1711.01558","title":"Wasserstein Auto-Encoders","created":"2017-11-05","cited_by_count":373},{"id":"2010.04053","title":"Fairness in Machine Learning: A Survey","created":"2020-10-04","cited_by_count":370},{"id":"1610.08452","title":"Fairness Beyond Disparate Treatment & Disparate Impact: Learning Classification without Disparate Mistreatment","created":"2016-10-26","cited_by_count":369},{"id":"1511.05644","title":"Adversarial Autoencoders","created":"2015-11-18","cited_by_count":364},{"id":"1706.00292","title":"Learning Generative Models with Sinkhorn Divergences","created":"2017-06-01","cited_by_count":314},{"id":"1705.08848","title":"Joint Distribution Optimal Transportation for Domain Adaptation","created":"2017-05-24","cited_by_count":282},{"id":"2002.02798","title":"How to train your neural ODE: the world of Jacobian and kinetic regularization","created":"2020-02-07","cited_by_count":228},{"id":"1310.4375","title":"Fast Computation of Wasserstein Barycenters","created":"2013-10-16","cited_by_count":216},{"id":"1803.10081","title":"DeepJDOT: Deep Joint Distribution Optimal Transport for Unsupervised Domain Adaptation","created":"2018-03-27","cited_by_count":214},{"id":"1902.00434","title":"Generalized Sliced Wasserstein Distances","created":"2019-02-01","cited_by_count":208},{"id":"1908.10962","title":"Optimal transport mapping via input convex neural networks","created":"2019-08-28","cited_by_count":206},{"id":"1506.05439","title":"Learning with a Wasserstein Loss","created":"2015-06-17","cited_by_count":196},{"id":"1805.09114","title":"Optimal Transport for structured data with application on graphs","created":"2018-05-23","cited_by_count":172},{"id":"1908.08729","title":"Wasserstein Distributionally Robust Optimization: Theory and Applications in Machine Learning","created":"2019-08-23","cited_by_count":170},{"id":"2002.02923","title":"Geometric Dataset Distances via Optimal Transport","created":"2020-02-07","cited_by_count":158},{"id":"2006.00104","title":"OT-Flow: Fast and Accurate Continuous Normalizing Flows via Optimal Transport","created":"2020-05-29","cited_by_count":143},{"id":"1508.07941","title":"Optimal Entropy-Transport problems and a new Hellinger-Kantorovich distance between positive measures","created":"2015-08-31","cited_by_count":139},{"id":"2201.12220","title":"Neural Optimal Transport","created":"2022-01-28","cited_by_count":126},{"id":"2103.03606","title":"Unbalanced minibatch Optimal Transport; applications to Domain Adaptation","created":"2021-03-05","cited_by_count":125},{"id":"1711.02283","title":"Large-Scale Optimal Transport and Mapping Estimation","created":"2017-11-07","cited_by_count":123},{"id":"1705.10743","title":"The Cramer Distance as a Solution to Biased Wasserstein Gradients","created":"2017-05-30","cited_by_count":119},{"id":"1904.05877","title":"Max-Sliced Wasserstein Distance and its use for GANs","created":"2019-04-11","cited_by_count":119},{"id":"1610.04420","title":"Theoretical Analysis of Domain Adaptation with Optimal Transport","created":"2016-10-14","cited_by_count":105},{"id":"2201.12324","title":"Optimal Transport Tools (OTT): A JAX Toolbox for all things Wasserstein","created":"2022-01-28","cited_by_count":101},{"id":"1909.13082","title":"Wasserstein-2 Generative Networks","created":"2019-09-28","cited_by_count":97},{"id":"2106.01954","title":"Do Neural Optimal Transport Solvers Work? A Continuous Wasserstein-2 Benchmark","created":"2021-06-03","cited_by_count":96},{"id":"1901.08949","title":"Subspace Robust Wasserstein Distances","created":"2019-01-25","cited_by_count":90},{"id":"1910.04091","title":"Learning with minibatch Wasserstein : asymptotic and gradient properties","created":"2019-10-09","cited_by_count":87},{"id":"2003.05783","title":"Statistical and Topological Properties of Sliced Probability Divergences","created":"2020-03-12","cited_by_count":85},{"id":"1710.10016","title":"Regularization via Mass Transportation","created":"2017-10-27","cited_by_count":81},{"id":"1803.04899","title":"Optimal Transport for Multi-source Domain Adaptation under Target Shift","created":"2018-03-13","cited_by_count":68},{"id":"2103.13843","title":"OTCE: A Transferability Metric for Cross-Domain Cross-Task Representations","created":"2021-03-25","cited_by_count":62},{"id":"1904.05408","title":"Sliced Wasserstein Generative Models","created":"2019-04-10","cited_by_count":61},{"id":"1711.05376","title":"Sliced Wasserstein Distance for Learning Gaussian Mixture Models","created":"2017-11-15","cited_by_count":59},{"id":"1805.11897","title":"Differential Properties of Sinkhorn Approximation for Learning with Wasserstein Distance","created":"2018-05-30","cited_by_count":56},{"id":"1307.5551","title":"Regularized Discrete Optimal Transport","created":"2013-07-21","cited_by_count":54},{"id":"2111.01177","title":"Don't Generate Me: Training Differentially Private Generative Models with Sinkhorn Divergence","created":"2021-11-01","cited_by_count":54},{"id":"1906.10827","title":"Hierarchical Optimal Transport for Document Representation","created":"2019-06-26","cited_by_count":53},{"id":"1409.6041","title":"Domain Adaptive Neural Networks for Object Recognition","created":"2014-09-21","cited_by_count":52},{"id":"2102.01752","title":"Continuous Wasserstein-2 Barycenter Estimation without Minimax Optimization","created":"2021-02-02","cited_by_count":51},{"id":"2007.04462","title":"Scalable Computations of Wasserstein Barycenter via Input Convex Neural Networks","created":"2020-07-08","cited_by_count":50},{"id":"2006.07458","title":"Projection Robust Wasserstein Distance and Riemannian Optimization","created":"2020-06-12","cited_by_count":45},{"id":"1704.02399","title":"Stein Variational Policy Gradient","created":"2017-04-07","cited_by_count":44},{"id":"1906.04516","title":"Asymptotic Guarantees for Learning Generative Models with the Sliced-Wasserstein Distance","created":"2019-06-11","cited_by_count":43},{"id":"2002.03731","title":"CO-Optimal Transport","created":"2020-02-10","cited_by_count":42},{"id":"2108.09645","title":"Improving Mini-batch Optimal Transport via Partial Transportation","created":"2021-08-22","cited_by_count":41},{"id":"1806.07348","title":"Statistical Optimal Transport via Factored Couplings","created":"2018-06-19","cited_by_count":38},{"id":"2102.06555","title":"Online Graph Dictionary Learning","created":"2021-02-12","cited_by_count":37},{"id":"1708.01955","title":"Wasserstein Dictionary Learning: Optimal Transport-based unsupervised non-linear dictionary learning","created":"2017-08-07","cited_by_count":35},{"id":"2103.01678","title":"Wasserstein GANs Work Because They Fail (to Approximate the Wasserstein Distance)","created":"2021-03-02","cited_by_count":35},{"id":"1808.03030","title":"Policy Optimization as Wasserstein Gradient Flows","created":"2018-08-09","cited_by_count":34},{"id":"1710.05488","title":"A Geometric View of Optimal Transportation and Generative Model","created":"2017-10-16","cited_by_count":31},{"id":"1712.06199","title":"Structured Optimal Transport","created":"2017-12-17","cited_by_count":31},{"id":"2206.08780","title":"Spherical Sliced-Wasserstein","created":"2022-06-17","cited_by_count":31},{"id":"1511.03206","title":"The Radon cumulative distribution transform and its application to image classification","created":"2015-11-10","cited_by_count":28},{"id":"2006.12938","title":"Multi-source Domain Adaptation via Weighted Joint Distributions Optimal Transport","created":"2020-06-23","cited_by_count":28},{"id":"1802.05570","title":"Optimal Transport: Fast Probabilistic Approximation with Exact Solvers","created":"2018-02-14","cited_by_count":27},{"id":"2010.12440","title":"Importance-Aware Semantic Segmentation in Self-Driving with Discrete Wasserstein Training","created":"2020-10-21","cited_by_count":27},{"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":"1911.08530","title":"Gromov-Wasserstein Factorization Models for Graph Clustering","created":"2019-11-19","cited_by_count":25},{"id":"2204.01188","title":"Revisiting Sliced Wasserstein on Images: From Vectorization to Convolution","created":"2022-04-04","cited_by_count":25},{"id":"2106.01070","title":"Testing Group Fairness via Optimal Transport Projections","created":"2021-06-02","cited_by_count":23},{"id":"1706.01807","title":"GAN and VAE from an Optimal Transport Point of View","created":"2017-06-06","cited_by_count":20},{"id":"2010.12760","title":"Dataset Dynamics via Gradient Flows in Probability Space","created":"2020-10-24","cited_by_count":18},{"id":"1910.03875","title":"How Well Do WGANs Estimate the Wasserstein Metric?","created":"2019-10-09","cited_by_count":17},{"id":"1801.07745","title":"Optimal Transport on Discrete Domains","created":"2018-01-23","cited_by_count":16},{"id":"1904.03936","title":"Wasserstein Adversarial Regularization (WAR) on label noise","created":"2019-04-08","cited_by_count":16},{"id":"1705.06189","title":"Co-clustering through Optimal Transport","created":"2017-05-17","cited_by_count":13},{"id":"1903.06753","title":"Wasserstein Distance based Deep Adversarial Transfer Learning for Intelligent Fault Diagnosis","created":"2019-03-02","cited_by_count":13},{"id":"1607.01179","title":"Robust clustering tools based on optimal transportation","created":"2016-07-05","cited_by_count":10},{"id":"1910.00888","title":"On the estimation of the Wasserstein distance in generative models","created":"2019-10-02","cited_by_count":6}],"next_cursor":null}