{"list":"other","total":57,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1702.08165","title":"Reinforcement Learning with Deep Energy-Based Policies","created":"2017-02-27","cited_by_count":669},{"id":"1608.04471","title":"Stein Variational Gradient Descent: A General Purpose Bayesian Inference Algorithm","created":"2016-08-16","cited_by_count":507},{"id":"2002.08791","title":"Bayesian Deep Learning and a Probabilistic Perspective of Generalization","created":"2020-02-20","cited_by_count":480},{"id":"1912.13213","title":"Online Learning: A Modern Introduction Using Convex Optimization","created":"2019-12-31","cited_by_count":417},{"id":"1502.05336","title":"Probabilistic Backpropagation for Scalable Learning of Bayesian Neural Networks","created":"2015-02-18","cited_by_count":295},{"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":"1903.08568","title":"Rapid Convergence of the Unadjusted Langevin Algorithm: Isoperimetry Suffices","created":"2019-03-20","cited_by_count":227},{"id":"1412.7392","title":"Theoretical guarantees for approximate sampling from smooth and log-concave densities","created":"2014-12-23","cited_by_count":208},{"id":"1801.06879","title":"Bayesian Deep Convolutional Encoder-Decoder Networks for Surrogate Modeling and Uncertainty Quantification","created":"2018-01-21","cited_by_count":199},{"id":"1507.05021","title":"Non-asymptotic convergence analysis for the Unadjusted Langevin Algorithm","created":"2015-07-17","cited_by_count":197},{"id":"1806.03836","title":"Bayesian Model-Agnostic Meta-Learning","created":"2018-06-11","cited_by_count":194},{"id":"1704.07520","title":"Stein Variational Gradient Descent as Gradient Flow","created":"2017-04-25","cited_by_count":152},{"id":"1506.04696","title":"A Complete Recipe for Stochastic Gradient MCMC","created":"2015-06-15","cited_by_count":146},{"id":"1605.01559","title":"High-dimensional Bayesian inference via the Unadjusted Langevin Algorithm","created":"2016-05-05","cited_by_count":146},{"id":"1602.02964","title":"A Kernel Test of Goodness of Fit","created":"2016-02-09","cited_by_count":143},{"id":"1602.04128","title":"Coin Betting and Parameter-Free Online Learning","created":"2016-02-12","cited_by_count":133},{"id":"1802.09188","title":"Analysis of Langevin Monte Carlo via convex optimization","created":"2018-02-26","cited_by_count":127},{"id":"1906.04370","title":"Maximum Mean Discrepancy Gradient Flow","created":"2019-06-11","cited_by_count":127},{"id":"1802.06293","title":"Black-Box Reductions for Parameter-free Online Learning in Banach Spaces","created":"2018-02-17","cited_by_count":125},{"id":"1802.08089","title":"Sampling as optimization in the space of measures: The Langevin dynamics as a composite optimization problem","created":"2018-02-22","cited_by_count":123},{"id":"1703.01717","title":"Measuring Sample Quality with Kernels","created":"2017-03-06","cited_by_count":119},{"id":"1710.00095","title":"User-friendly guarantees for the Langevin Monte Carlo with inaccurate gradient","created":"2017-09-29","cited_by_count":116},{"id":"1705.09048","title":"Convergence of Langevin MCMC in KL-divergence","created":"2017-05-25","cited_by_count":88},{"id":"1912.00894","title":"On the geometry of Stein variational gradient descent","created":"2019-12-02","cited_by_count":82},{"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":"2006.09797","title":"A Non-Asymptotic Analysis for Stein Variational Gradient Descent","created":"2020-06-17","cited_by_count":61},{"id":"2202.13460","title":"Conditional Simulation Using Diffusion Schr\\\"odinger Bridges","created":"2022-02-27","cited_by_count":60},{"id":"2105.09994","title":"Kernel Stein Discrepancy Descent","created":"2021-05-20","cited_by_count":57},{"id":"1806.03085","title":"A Stein variational Newton method","created":"2018-06-08","cited_by_count":50},{"id":"1711.04425","title":"Message Passing Stein Variational Gradient Descent","created":"2017-11-13","cited_by_count":47},{"id":"1710.07876","title":"Optimal transport for Gaussian mixture models","created":"2017-10-22","cited_by_count":45},{"id":"1805.11659","title":"A Unified Particle-Optimization Framework for Scalable Bayesian Sampling","created":"2018-05-29","cited_by_count":44},{"id":"1803.10161","title":"Stein Points","created":"2018-03-27","cited_by_count":43},{"id":"1808.03030","title":"Policy Optimization as Wasserstein Gradient Flows","created":"2018-08-09","cited_by_count":34},{"id":"2008.10087","title":"Blindness of score-based methods to isolated components and mixing proportions","created":"2020-08-23","cited_by_count":34},{"id":"2002.03469","title":"Projected Stein Variational Gradient Descent","created":"2020-02-09","cited_by_count":33},{"id":"1910.12794","title":"Stein Variational Gradient Descent With Matrix-Valued Kernels","created":"2019-10-28","cited_by_count":32},{"id":"1707.06626","title":"Learning to Draw Samples with Amortized Stein Variational Gradient Descent","created":"2017-07-20","cited_by_count":28},{"id":"1902.01500","title":"Parameter-Free Online Convex Optimization with Sub-Exponential Noise","created":"2019-02-05","cited_by_count":28},{"id":"1406.3816","title":"Simultaneous Model Selection and Optimization through Parameter-free Stochastic Learning","created":"2014-06-15","cited_by_count":27},{"id":"1711.11216","title":"Riemannian Stein Variational Gradient Descent for Bayesian Inference","created":"2017-11-30","cited_by_count":24},{"id":"2006.16531","title":"Sliced Kernelized Stein Discrepancy","created":"2020-06-30","cited_by_count":23},{"id":"2211.09721","title":"A Finite-Particle Convergence Rate for Stein Variational Gradient Descent","created":"2022-11-17","cited_by_count":22},{"id":"1611.01722","title":"Learning to Draw Samples: With Application to Amortized MLE for Generative Adversarial Learning","created":"2016-11-06","cited_by_count":21},{"id":"2106.03076","title":"A Convergence Theory for SVGD in the Population Limit under Talagrand's Inequality T1","created":"2021-06-06","cited_by_count":21},{"id":"2006.07507","title":"Better Parameter-free Stochastic Optimization with ODE Updates for Coin-Betting","created":"2020-06-12","cited_by_count":19},{"id":"2210.13400","title":"Sampling with Mollified Interaction Energy Descent","created":"2022-10-24","cited_by_count":17},{"id":"1902.00282","title":"Understanding MCMC Dynamics as Flows on the Wasserstein Space","created":"2019-02-01","cited_by_count":14},{"id":"1806.02775","title":"Stein Variational Gradient Descent Without Gradient","created":"2018-06-07","cited_by_count":12},{"id":"2202.03297","title":"Grassmann Stein Variational Gradient Descent","created":"2022-02-07","cited_by_count":12},{"id":"2202.00755","title":"Lagrangian Manifold Monte Carlo on Monge Patches","created":"2022-02-01","cited_by_count":11},{"id":"1805.07912","title":"Bayesian posterior approximation via greedy particle optimization","created":"2018-05-21","cited_by_count":10},{"id":"2203.10327","title":"Implicit Parameter-free Online Learning with Truncated Linear Models","created":"2022-03-19","cited_by_count":8},{"id":"2002.09070","title":"Stein Self-Repulsive Dynamics: Benefits From Past Samples","created":"2020-02-21","cited_by_count":6},{"id":"2202.04732","title":"Online Learning to Transport via the Minimal Selection Principle","created":"2022-02-09","cited_by_count":6},{"id":"2210.00462","title":"Improved Stein Variational Gradient Descent with Importance Weights","created":"2022-10-02","cited_by_count":2}],"next_cursor":null}