{"list":"other","total":72,"rows":[{"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":"1608.03983","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","created":"2016-08-13","cited_by_count":5045},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"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":"1703.06114","title":"Deep Sets","created":"2017-03-10","cited_by_count":1421},{"id":"2012.09688","title":"PCT: Point cloud transformer","created":"2020-12-17","cited_by_count":732},{"id":"1805.00909","title":"Reinforcement Learning and Control as Probabilistic Inference: Tutorial and Review","created":"2018-05-02","cited_by_count":482},{"id":"1507.00504","title":"Optimal Transport for Domain Adaptation","created":"2015-07-02","cited_by_count":463},{"id":"1902.00434","title":"Generalized Sliced Wasserstein Distances","created":"2019-02-01","cited_by_count":208},{"id":"2002.02923","title":"Geometric Dataset Distances via Optimal Transport","created":"2020-02-07","cited_by_count":158},{"id":"2006.04678","title":"Primal Wasserstein Imitation Learning","created":"2020-06-08","cited_by_count":121},{"id":"1904.05877","title":"Max-Sliced Wasserstein Distance and its use for GANs","created":"2019-04-11","cited_by_count":119},{"id":"1906.01277","title":"Wasserstein Weisfeiler-Lehman Graph Kernels","created":"2019-06-04","cited_by_count":104},{"id":"1909.13082","title":"Wasserstein-2 Generative Networks","created":"2019-09-28","cited_by_count":97},{"id":"1901.08949","title":"Subspace Robust Wasserstein Distances","created":"2019-01-25","cited_by_count":90},{"id":"2003.05783","title":"Statistical and Topological Properties of Sliced Probability Divergences","created":"2020-03-12","cited_by_count":85},{"id":"2110.02999","title":"Generative Modeling with Optimal Transport Maps","created":"2021-10-06","cited_by_count":82},{"id":"2001.09394","title":"Lagrangian Duality for Constrained Deep Learning","created":"2020-01-26","cited_by_count":74},{"id":"2002.07367","title":"Distributional Sliced-Wasserstein and Applications to Generative Modeling","created":"2020-02-18","cited_by_count":69},{"id":"2006.16038","title":"SoftSort: A Continuous Relaxation for the argsort Operator","created":"2020-06-29","cited_by_count":66},{"id":"2306.16156","title":"Recent Advances in Optimal Transport for Machine Learning","created":"2023-06-28","cited_by_count":66},{"id":"1511.03198","title":"Sliced Wasserstein Kernels for Probability Distributions","created":"2015-11-10","cited_by_count":65},{"id":"1906.08113","title":"Wasserstein Adversarial Imitation Learning","created":"2019-06-19","cited_by_count":60},{"id":"1711.05376","title":"Sliced Wasserstein Distance for Learning Gaussian Mixture Models","created":"2017-11-15","cited_by_count":59},{"id":"2006.09430","title":"Wasserstein Embedding for Graph Learning","created":"2020-06-16","cited_by_count":56},{"id":"2201.03299","title":"Avoiding Overfitting: A Survey on Regularization Methods for Convolutional Neural Networks","created":"2022-01-10","cited_by_count":55},{"id":"2109.06332","title":"Achieving Zero Constraint Violation for Constrained Reinforcement Learning via Primal-Dual Approach","created":"2021-09-13","cited_by_count":50},{"id":"2006.05487","title":"Probably Approximately Correct Constrained Learning","created":"2020-06-09","cited_by_count":47},{"id":"2103.05134","title":"Constrained Learning with Non-Convex Losses","created":"2021-03-08","cited_by_count":42},{"id":"1807.08088","title":"Learning Optimal Resource Allocations in Wireless Systems","created":"2018-07-21","cited_by_count":40},{"id":"1905.08786","title":"Maximum Entropy-Regularized Multi-Goal Reinforcement Learning","created":"2019-05-21","cited_by_count":40},{"id":"2102.11941","title":"State Augmented Constrained Reinforcement Learning: Overcoming the Limitations of Learning with Rewards","created":"2021-02-23","cited_by_count":40},{"id":"2304.13586","title":"Energy-Based Sliced Wasserstein Distance","created":"2023-04-26","cited_by_count":39},{"id":"2007.00674","title":"Sliced Iterative Normalizing Flows","created":"2020-07-01","cited_by_count":38},{"id":"1808.03030","title":"Policy Optimization as Wasserstein Gradient Flows","created":"2018-08-09","cited_by_count":34},{"id":"2106.15427","title":"Fast Approximation of the Sliced-Wasserstein Distance Using Concentration of Random Projections","created":"2021-06-29","cited_by_count":33},{"id":"1901.06566","title":"Overfitting Mechanism and Avoidance in Deep Neural Networks","created":"2019-01-19","cited_by_count":30},{"id":"1511.03206","title":"The Radon cumulative distribution transform and its application to image classification","created":"2015-11-10","cited_by_count":28},{"id":"2008.12967","title":"Unpaired Deep Learning for Accelerated MRI using Optimal Transport Driven CycleGAN","created":"2020-08-29","cited_by_count":28},{"id":"2208.04425","title":"Controlled Sparsity via Constrained Optimization or: How I Learned to Stop Tuning Penalties and Love Constraints","created":"2022-08-08","cited_by_count":25},{"id":"2202.04108","title":"A Lagrangian Duality Approach to Active Learning","created":"2022-02-08","cited_by_count":24},{"id":"2010.05380","title":"Efficient Wasserstein Natural Gradients for Reinforcement Learning","created":"2020-10-12","cited_by_count":23},{"id":"2209.13570","title":"Hierarchical Sliced Wasserstein Distance","created":"2022-09-27","cited_by_count":23},{"id":"2410.12176","title":"Expected Sliced Transport Plans","created":"2024-10-16","cited_by_count":19},{"id":"2301.03377","title":"Machine Learning for Large-Scale Optimization in 6G Wireless Networks","created":"2023-01-03","cited_by_count":18},{"id":"2502.17504","title":"Protein Large Language Models: A Comprehensive Survey","created":"2025-02-21","cited_by_count":18},{"id":"2203.11012","title":"Learning Resilient Radio Resource Management Policies with Graph Neural Networks","created":"2022-03-07","cited_by_count":17},{"id":"2010.08669","title":"Robot Learning with Crash Constraints","created":"2020-10-16","cited_by_count":15},{"id":"2306.02342","title":"Deep Optimal Transport: A Practical Algorithm for Photo-realistic Image Restoration","created":"2023-06-04","cited_by_count":15},{"id":"2306.02426","title":"Resilient Constrained Learning","created":"2023-06-04","cited_by_count":15},{"id":"2004.03669","title":"Radon cumulative distribution transform subspace modeling for image classification","created":"2020-04-07","cited_by_count":14},{"id":"2006.08812","title":"Augmented Sliced Wasserstein Distances","created":"2020-06-15","cited_by_count":14},{"id":"2404.09411","title":"Wasserstein Wormhole: Scalable Optimal Transport Distance with Transformers","created":"2024-04-15","cited_by_count":14},{"id":"1705.06189","title":"Co-clustering through Optimal Transport","created":"2017-05-17","cited_by_count":13},{"id":"2402.02239","title":"Distributional Reduction: Unifying Dimensionality Reduction and Clustering with Gromov-Wasserstein","created":"2024-02-03","cited_by_count":12},{"id":"2301.03749","title":"Markovian Sliced Wasserstein Distances: Beyond Independent Projections","created":"2023-01-10","cited_by_count":11},{"id":"2407.18322","title":"The Need for Guardrails with Large Language Models in Medical Safety-Critical Settings: An Artificial Intelligence Application in the Pharmacovigilance Ecosystem","created":"2024-07-01","cited_by_count":11},{"id":"2010.09921","title":"Sufficient dimension reduction for classification using principal optimal transport direction","created":"2020-10-19","cited_by_count":10},{"id":"2502.07962","title":"ESPFormer: Doubly-Stochastic Attention with Expected Sliced Transport Plans","created":"2025-02-11","cited_by_count":10},{"id":"2112.05872","title":"SLOSH: Set LOcality Sensitive Hashing via Sliced-Wasserstein Embeddings","created":"2021-12-11","cited_by_count":9},{"id":"2306.07818","title":"A Primal-Dual-Critic Algorithm for Offline Constrained Reinforcement Learning","created":"2023-06-13","cited_by_count":9},{"id":"2212.01174","title":"Utilizing Prior Solutions for Reward Shaping and Composition in Entropy-Regularized Reinforcement Learning","created":"2022-12-02","cited_by_count":8},{"id":"2504.02544","title":"Fourier Sliced-Wasserstein Embedding for Multisets and Measures","created":"2025-04-03","cited_by_count":8},{"id":"2409.17190","title":"Enhancing Guardrails for Safe and Secure Healthcare AI","created":"2024-09-25","cited_by_count":7},{"id":"2411.14487","title":"Ensuring Safety and Trust: Analyzing the Risks of Large Language Models in Medicine","created":"2024-11-20","cited_by_count":7},{"id":"2501.14912","title":"Feasible Learning","created":"2025-01-24","cited_by_count":5},{"id":"2310.00154","title":"Primal Dual Continual Learning: Balancing Stability and Plasticity through Adaptive Memory Allocation","created":"2023-09-29","cited_by_count":4},{"id":"2411.06055","title":"Linear Spherical Sliced Optimal Transport: A Fast Metric for Comparing Spherical Data","created":"2024-11-09","cited_by_count":4},{"id":"2001.06944","title":"Nested-Wasserstein Self-Imitation Learning for Sequence Generation","created":"2020-01-20","cited_by_count":3},{"id":"2306.05553","title":"Equivariant vs. Invariant Layers: A Comparison of Backbone and Pooling for Point Cloud Classification","created":"2023-06-08","cited_by_count":2},{"id":"2411.10651","title":"Understanding Learning with Sliced-Wasserstein Requires Rethinking Informative Slices","created":"2024-11-16","cited_by_count":2}],"next_cursor":null}