{"list":"other","total":57,"rows":[{"id":"1601.00670","title":"Variational Inference: A Review for Statisticians","created":"2016-01-04","cited_by_count":1472},{"id":"1801.01401","title":"Demystifying MMD GANs","created":"2018-01-04","cited_by_count":1293},{"id":"1502.02761","title":"Generative Moment Matching Networks","created":"2015-02-10","cited_by_count":257},{"id":"1705.08584","title":"MMD GAN: Towards Deeper Understanding of Moment Matching Network","created":"2017-05-24","cited_by_count":254},{"id":"1602.03253","title":"A Kernelized Stein Discrepancy for Goodness-of-fit Tests and Model Evaluation","created":"2016-02-10","cited_by_count":236},{"id":"1806.05500","title":"Statistical Aspects of Wasserstein Distances","created":"2018-06-14","cited_by_count":203},{"id":"1301.2294","title":"Expectation Propagation for approximate Bayesian inference","created":"2013-01-10","cited_by_count":174},{"id":"1505.03906","title":"Training generative neural networks via Maximum Mean Discrepancy optimization","created":"2015-05-14","cited_by_count":151},{"id":"1602.02964","title":"A Kernel Test of Goodness of Fit","created":"2016-02-09","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":"1906.04370","title":"Maximum Mean Discrepancy Gradient Flow","created":"2019-06-11","cited_by_count":127},{"id":"1703.01717","title":"Measuring Sample Quality with Kernels","created":"2017-03-06","cited_by_count":119},{"id":"2107.04562","title":"The Bayesian Learning Rule","created":"2021-07-09","cited_by_count":99},{"id":"2205.15902","title":"Variational inference via Wasserstein gradient flows","created":"2022-05-31","cited_by_count":85},{"id":"1912.00894","title":"On the geometry of Stein variational gradient descent","created":"2019-12-02","cited_by_count":82},{"id":"2402.17641","title":"Variational Learning is Effective for Large Deep Networks","created":"2024-02-27","cited_by_count":65},{"id":"2006.02509","title":"SVGD as a kernelized Wasserstein gradient flow of the chi-squared divergence","created":"2020-06-03","cited_by_count":64},{"id":"2202.01009","title":"Mean-Field Langevin Dynamics: Exponential Convergence and Annealing","created":"2022-02-02","cited_by_count":61},{"id":"1906.08283","title":"Minimum Stein Discrepancy Estimators","created":"2019-06-19","cited_by_count":57},{"id":"2105.09994","title":"Kernel Stein Discrepancy Descent","created":"2021-05-20","cited_by_count":57},{"id":"1811.02002","title":"Finding Mixed Nash Equilibria of Generative Adversarial Networks","created":"2018-10-23","cited_by_count":49},{"id":"2407.18163","title":"Statistical optimal transport","created":"2024-07-25","cited_by_count":47},{"id":"2003.10374","title":"Markovian Score Climbing: Variational Inference with KL(p||q)","created":"2020-03-23","cited_by_count":46},{"id":"2402.01258","title":"Transformers Learn Nonlinear Features In Context: Nonconvex Mean-field Dynamics on the Attention Landscape","created":"2024-02-02","cited_by_count":46},{"id":"1905.09863","title":"Accelerating Langevin Sampling with Birth-death","created":"2019-05-23","cited_by_count":45},{"id":"2012.00780","title":"Refining Deep Generative Models via Discriminator Gradient Flow","created":"2020-12-01","cited_by_count":45},{"id":"1803.10161","title":"Stein Points","created":"2018-03-27","cited_by_count":43},{"id":"2103.01085","title":"Challenges and Opportunities in High-dimensional Variational Inference","created":"2021-03-01","cited_by_count":35},{"id":"2206.08873","title":"Mirror Descent with Relative Smoothness in Measure Spaces, with application to Sinkhorn and EM","created":"2022-06-17","cited_by_count":34},{"id":"2211.00450","title":"Birth-death dynamics for sampling: Global convergence, approximations and their asymptotics","created":"2022-11-01","cited_by_count":30},{"id":"2106.15980","title":"Variational Refinement for Importance Sampling Using the Forward Kullback-Leibler Divergence","created":"2021-06-30","cited_by_count":29},{"id":"2002.06277","title":"A mean-field analysis of two-player zero-sum games","created":"2020-02-14","cited_by_count":28},{"id":"2301.01766","title":"Learning Gaussian Mixtures Using the Wasserstein-Fisher-Rao Gradient Flow","created":"2023-01-04","cited_by_count":27},{"id":"2401.03892","title":"Sampling in Unit Time with Kernel Fisher-Rao Flow","created":"2024-01-08","cited_by_count":27},{"id":"2310.03054","title":"Posterior Sampling Based on Gradient Flows of the MMD with Negative Distance Kernel","created":"2023-10-04","cited_by_count":25},{"id":"1506.03101","title":"Provable Bayesian Inference via Particle Mirror Descent","created":"2015-06-09","cited_by_count":23},{"id":"2305.16150","title":"Unifying GANs and Score-Based Diffusion as Generative Particle Models","created":"2023-05-25","cited_by_count":21},{"id":"2211.07861","title":"Regularized Stein Variational Gradient Flow","created":"2022-11-15","cited_by_count":19},{"id":"2405.06780","title":"Deep MMD Gradient Flow without adversarial training","created":"2024-05-10","cited_by_count":19},{"id":"2007.07105","title":"Estimating Barycenters of Measures in High Dimensions","created":"2020-07-14","cited_by_count":18},{"id":"2302.11024","title":"Gradient Flows for Sampling: Mean-Field Models, Gaussian Approximations and Affine Invariance","created":"2023-02-21","cited_by_count":16},{"id":"2310.11914","title":"A connection between Tempering and Entropic Mirror Descent","created":"2023-10-18","cited_by_count":16},{"id":"2409.14980","title":"(De)-regularized Maximum Mean Discrepancy Gradient Flow","created":"2024-09-23","cited_by_count":16},{"id":"2402.04613","title":"Wasserstein Gradient Flows for Moreau Envelopes of f-Divergences in Reproducing Kernel Hilbert Spaces","created":"2024-02-07","cited_by_count":15},{"id":"2211.01280","title":"An Exponentially Converging Particle Method for the Mixed Nash Equilibrium of Continuous Games","created":"2022-11-02","cited_by_count":14},{"id":"2302.01075","title":"MonoFlow: Rethinking Divergence GANs via the Perspective of Wasserstein Gradient Flows","created":"2023-02-02","cited_by_count":13},{"id":"2407.15693","title":"Fisher-Rao Gradient Flow: Geodesic Convexity and Functional Inequalities","created":"2024-07-22","cited_by_count":13},{"id":"2009.14148","title":"Unbalanced Sobolev Descent","created":"2020-09-29","cited_by_count":11},{"id":"2409.01464","title":"Stein transport for Bayesian inference","created":"2024-09-02","cited_by_count":11},{"id":"1805.07912","title":"Bayesian posterior approximation via greedy particle optimization","created":"2018-05-21","cited_by_count":10},{"id":"2202.01841","title":"Transport Score Climbing: Variational Inference Using Forward KL and Adaptive Neural Transport","created":"2022-02-03","cited_by_count":8},{"id":"2310.20090","title":"Bridging the Gap Between Variational Inference and Wasserstein Gradient Flows","created":"2023-10-31","cited_by_count":8},{"id":"2403.10610","title":"Sequential Monte Carlo for Inclusive KL Minimization in Amortized Variational Inference","created":"2024-03-15","cited_by_count":7},{"id":"2410.20622","title":"Kernel Approximation of Fisher-Rao Gradient Flows","created":"2024-10-27","cited_by_count":7},{"id":"2202.12927","title":"A blob method for inhomogeneous diffusion with applications to multi-agent control and sampling","created":"2022-02-25","cited_by_count":6},{"id":"2403.00147","title":"Analysis of Kernel Mirror Prox for Measure Optimization","created":"2024-02-29","cited_by_count":4},{"id":"2303.03714","title":"Generative Modeling with Flow-Guided Density Ratio Learning","created":"2023-03-07","cited_by_count":2}],"next_cursor":null}