{"total":52,"rows":[{"id":"2110.11773","title":"Sinkformers: Transformers with Doubly Stochastic Attention","created":"2021-10-22","cited_by_count":138,"area":null},{"id":"2201.12324","title":"Optimal Transport Tools (OTT): A JAX Toolbox for all things Wasserstein","created":"2022-01-28","cited_by_count":101,"area":null},{"id":"2306.16156","title":"Recent Advances in Optimal Transport for Machine Learning","created":"2023-06-28","cited_by_count":66,"area":null},{"id":"2107.01718","title":"Rates of Estimation of Optimal Transport Maps using Plug-in Estimators via Barycentric Projections","created":"2021-07-04","cited_by_count":53,"area":null},{"id":"2109.11926","title":"Sinkhorn Distributionally Robust Optimization","created":"2021-09-24","cited_by_count":38,"area":null},{"id":"2106.02968","title":"Low Budget Active Learning via Wasserstein Distance: An Integer Programming Approach","created":"2021-06-05","cited_by_count":34,"area":null},{"id":"2209.13091","title":"WaterNeRF: Neural Radiance Fields for Underwater Scenes","created":"2022-09-27","cited_by_count":29,"area":null},{"id":"2205.06688","title":"A Unified Framework for Implicit Sinkhorn Differentiation","created":"2022-05-13","cited_by_count":28,"area":null},{"id":"2305.13768","title":"One-step differentiation of iterative algorithms","created":"2023-05-23","cited_by_count":28,"area":null},{"id":"2202.03813","title":"Learning to Predict Graphs with Fused Gromov-Wasserstein Barycenters","created":"2022-02-08","cited_by_count":22,"area":null},{"id":"2107.03021","title":"Bi-level Feature Alignment for Versatile Image Translation and Manipulation","created":"2021-07-07","cited_by_count":20,"area":null},{"id":"2112.08189","title":"ST-MTL: Spatio-Temporal Multitask Learning Model to Predict Scanpath While Tracking Instruments in Robotic Surgery","created":"2021-12-10","cited_by_count":20,"area":null},{"id":"2107.12270","title":"Adaptive Hierarchical Graph Reasoning with Semantic Coherence for Video-and-Language Inference","created":"2021-07-26","cited_by_count":18,"area":null},{"id":"2111.06888","title":"Learning Generalized Gumbel-max Causal Mechanisms","created":"2021-11-11","cited_by_count":16,"area":null},{"id":"2206.07630","title":"Rethinking Initialization of the Sinkhorn Algorithm","created":"2022-06-15","cited_by_count":14,"area":null},{"id":"2401.12253","title":"Accelerating Sinkhorn Algorithm with Sparse Newton Iterations","created":"2024-01-20","cited_by_count":11,"area":null},{"id":"2211.07096","title":"Alternating Implicit Projected SGD and Its Efficient Variants for Equality-constrained Bilevel Optimization","created":"2022-11-14","cited_by_count":10,"area":null},{"id":"2207.12717","title":"The derivatives of Sinkhorn-Knopp converge","created":"2022-07-26","cited_by_count":9,"area":null},{"id":"2103.00394","title":"Convergence of Gaussian-smoothed optimal transport distance with sub-gamma distributions and dependent samples","created":"2021-02-28","cited_by_count":8,"area":null},{"id":"2109.10919","title":"An Exploration of Learnt Representations of W Jets","created":"2021-09-22","cited_by_count":8,"area":null},{"id":"2405.19532","title":"Contrasting Multiple Representations with the Multi-Marginal Matching Gap","created":"2024-05-29","cited_by_count":8,"area":null},{"id":"2109.04442","title":"FGOT: Graph Distances based on Filters and Optimal Transport","created":"2021-09-09","cited_by_count":7,"area":null},{"id":"2405.02962","title":"VectorPainter: Advanced Stylized Vector Graphics Synthesis Using Stroke-Style Priors","created":"2024-05-05","cited_by_count":7,"area":null},{"id":"2405.03664","title":"A New Robust Partial $p$-Wasserstein-Based Metric for Comparing Distributions","created":"2024-05-06","cited_by_count":7,"area":null},{"id":"2202.12404","title":"Exploiting Problem Structure in Deep Declarative Networks: Two Case Studies","created":"2022-02-24","cited_by_count":6,"area":null},{"id":"2105.14244","title":"Learning Graphon Autoencoders for Generative Graph Modeling","created":"2021-05-29","cited_by_count":5,"area":null},{"id":"2405.15673","title":"Consistency of Neural Causal Partial Identification","created":"2024-05-24","cited_by_count":5,"area":null},{"id":"2105.14337","title":"Optimal transport with $f$-divergence regularization and generalized Sinkhorn algorithm","created":"2021-05-29","cited_by_count":4,"area":null},{"id":"2405.15441","title":"Statistical and Computational Guarantees of Kernel Max-Sliced Wasserstein Distances","created":"2024-05-24","cited_by_count":4,"area":null},{"id":"2103.11265","title":"Bayesian Distributional Policy Gradients","created":"2021-03-20","cited_by_count":3,"area":null},{"id":"2210.11489","title":"Machine-Learning Compression for Particle Physics Discoveries","created":"2022-10-20","cited_by_count":3,"area":null},{"id":"2401.08978","title":"Trade-off Between Dependence and Complexity for Nonparametric Learning -- an Empirical Process Approach","created":"2024-01-17","cited_by_count":3,"area":null},{"id":"2403.05054","title":"A Sinkhorn-type Algorithm for Constrained Optimal Transport","created":"2024-03-08","cited_by_count":3,"area":null},{"id":"2404.11868","title":"OTCXR: Rethinking Self-supervised Alignment using Optimal Transport for Chest X-ray Analysis","created":"2024-04-18","cited_by_count":3,"area":null},{"id":"2411.11875","title":"Exploring Optimal Transport-Based Multi-Grained Alignments for Text-Molecule Retrieval","created":"2024-11-04","cited_by_count":3,"area":null},{"id":"2112.03024","title":"Domain-oriented Language Pre-training with Adaptive Hybrid Masking and Optimal Transport Alignment","created":"2021-12-01","cited_by_count":2,"area":null},{"id":"2209.01498","title":"StreamNet: A WAE for White Matter Streamline Analysis","created":"2022-09-03","cited_by_count":2,"area":null},{"id":"2406.08399","title":"Differentiable Cost-Parameterized Monge Map Estimators","created":"2024-06-12","cited_by_count":2,"area":null},{"id":"2510.11227","title":"Enforcing convex constraints in Graph Neural Networks","created":"2025-10-13","cited_by_count":2,"area":null},{"id":"2307.10099","title":"Memory Efficient And Minimax Distribution Estimation Under Wasserstein Distance Using Bayesian Histograms","created":"2023-07-19","cited_by_count":1,"area":null},{"id":"2308.09228","title":"Generalized Sum Pooling for Metric Learning","created":"2023-08-18","cited_by_count":1,"area":null},{"id":"2409.15088","title":"AdapFair: Ensuring Adaptive Fairness for Machine Learning Operations","created":"2024-09-23","cited_by_count":1,"area":null},{"id":"2410.14029","title":"Auditing and Enforcing Conditional Fairness via Optimal Transport","created":"2024-10-17","cited_by_count":1,"area":null},{"id":"2506.14780","title":"Faster Computation of Entropic Optimal Transport via Stable Low Frequency Modes","created":"2025-05-23","cited_by_count":1,"area":null},{"id":"2102.07956","title":"Efficient Discretizations of Optimal Transport","created":"2021-02-16","cited_by_count":0,"area":null},{"id":"2310.18586","title":"Optimal Transport for Kernel Gaussian Mixture Models","created":"2023-10-28","cited_by_count":0,"area":null},{"id":"2509.02109","title":"Differentiable Expectation-Maximisation and Applications to Gaussian Mixture Model Optimal Transport","created":"2025-09-02","cited_by_count":0,"area":null},{"id":"2601.16366","title":"Post-Training Neural Network Pruning using Graph Curvature","created":"2026-01-22","cited_by_count":0,"area":null},{"id":"2605.08123","title":"Block-Wise Differentiable Sinkhorn Attention: Tail-Refinement Gradients with a Gap-Aware Dustbin Bridge","created":"2026-04-28","cited_by_count":0,"area":null},{"id":"2605.08928","title":"Learning Generative Dynamics with Soft Law Constraints: A McKean-Vlasov FBSDE Approach","created":"2026-05-09","cited_by_count":0,"area":null},{"id":"2605.11710","title":"Unlocking Compositional Generalization in Continual Few-Shot Learning","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2608.13418","title":"Wasserstein Filtering: A Sample Selection Method for Robust Distribution Learning","created":"2026-08-13","cited_by_count":0,"area":null}],"next_cursor":null}