{"list":"other","total":52,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1601.00670","title":"Variational Inference: A Review for Statisticians","created":"2016-01-04","cited_by_count":1472},{"id":"1904.09237","title":"On the Convergence of Adam and Beyond","created":"2019-04-19","cited_by_count":841},{"id":"1608.04636","title":"Linear Convergence of Gradient and Proximal-Gradient Methods Under the Polyak-\\L{}ojasiewicz Condition","created":"2016-08-16","cited_by_count":539},{"id":"1810.09538","title":"Pyro: Deep Universal Probabilistic Programming","created":"2018-10-18","cited_by_count":380},{"id":"1401.0118","title":"Black Box Variational Inference","created":"2013-12-31","cited_by_count":319},{"id":"1711.05597","title":"Advances in Variational Inference","created":"2017-11-15","cited_by_count":236},{"id":"1901.09401","title":"SGD: General Analysis and Improved Rates","created":"2019-01-27","cited_by_count":207},{"id":"2301.11235","title":"Handbook of Convergence Theorems for (Stochastic) Gradient Methods","created":"2023-01-26","cited_by_count":163},{"id":"1603.00788","title":"Automatic Differentiation Variational Inference","created":"2016-03-02","cited_by_count":159},{"id":"2002.03329","title":"Better Theory for SGD in the Nonconvex World","created":"2020-02-09","cited_by_count":158},{"id":"1810.07288","title":"Fast and Faster Convergence of SGD for Over-Parameterized Models and an Accelerated Perceptron","created":"2018-10-16","cited_by_count":143},{"id":"1801.02309","title":"Log-concave sampling: Metropolis-Hastings algorithms are fast","created":"2018-01-08","cited_by_count":118},{"id":"2006.05988","title":"Random Reshuffling: Simple Analysis with Vast Improvements","created":"2020-06-10","cited_by_count":115},{"id":"2208.09632","title":"Adam Can Converge Without Any Modification On Update Rules","created":"2022-08-20","cited_by_count":114},{"id":"2304.13960","title":"Noise Is Not the Main Factor Behind the Gap Between SGD and Adam on Transformers, but Sign Descent Might Be","created":"2023-04-27","cited_by_count":114},{"id":"1711.10604","title":"TensorFlow Distributions","created":"2017-11-28","cited_by_count":106},{"id":"1703.09194","title":"Sticking the Landing: Simple, Lower-Variance Gradient Estimators for Variational Inference","created":"2017-03-27","cited_by_count":98},{"id":"1802.03801","title":"SGD and Hogwild! Convergence Without the Bounded Gradients Assumption","created":"2018-02-11","cited_by_count":95},{"id":"2205.15902","title":"Variational inference via Wasserstein gradient flows","created":"2022-05-31","cited_by_count":85},{"id":"1905.11261","title":"A Unified Theory of SGD: Variance Reduction, Sampling, Quantization and Coordinate Descent","created":"2019-05-27","cited_by_count":84},{"id":"1806.10077","title":"Random Shuffling Beats SGD after Finite Epochs","created":"2018-06-26","cited_by_count":67},{"id":"1706.09293","title":"Concentration of tempered posteriors and of their variational approximations","created":"2017-06-28","cited_by_count":66},{"id":"1703.04265","title":"Conjugate-Computation Variational Inference : Converting Variational Inference in Non-Conjugate Models to Inferences in Conjugate Models","created":"2017-03-13","cited_by_count":65},{"id":"1903.01463","title":"SGD without Replacement: Sharper Rates for General Smooth Convex Functions","created":"2019-03-04","cited_by_count":61},{"id":"2006.06946","title":"SGD with shuffling: optimal rates without component convexity and large epoch requirements","created":"2020-06-12","cited_by_count":58},{"id":"1802.02538","title":"Yes, but Did It Work?: Evaluating Variational Inference","created":"2018-02-07","cited_by_count":53},{"id":"1906.02914","title":"Fast and Simple Natural-Gradient Variational Inference with Mixture of Exponential-family Approximations","created":"2019-06-07","cited_by_count":51},{"id":"2003.10374","title":"Markovian Score Climbing: Variational Inference with KL(p||q)","created":"2020-03-23","cited_by_count":46},{"id":"1809.10330","title":"Variance reduction properties of the reparameterization trick","created":"2018-09-27","cited_by_count":41},{"id":"1709.02536","title":"Covariances, Robustness, and Variational Bayes","created":"2017-09-08","cited_by_count":40},{"id":"1511.03243","title":"Black-box $\\alpha$-divergence Minimization","created":"2015-11-10","cited_by_count":37},{"id":"2006.10343","title":"Advances in Black-Box VI: Normalizing Flows, Importance Weighting, and Optimization","created":"2020-06-18","cited_by_count":37},{"id":"2304.05398","title":"Forward-backward Gaussian variational inference via JKO in the Bures-Wasserstein Space","created":"2023-04-10","cited_by_count":36},{"id":"2103.01085","title":"Challenges and Opportunities in High-dimensional Variational Inference","created":"2021-03-01","cited_by_count":35},{"id":"1901.08431","title":"Provable Smoothness Guarantees for Black-Box Variational Inference","created":"2019-01-24","cited_by_count":29},{"id":"1807.01604","title":"Quasi-Monte Carlo Variational Inference","created":"2018-07-04","cited_by_count":24},{"id":"1905.10859","title":"Variational Bayes under Model Misspecification","created":"2019-05-26","cited_by_count":22},{"id":"1906.08241","title":"Provable Gradient Variance Guarantees for Black-Box Variational Inference","created":"2019-06-19","cited_by_count":21},{"id":"2009.00666","title":"Robust, Accurate Stochastic Optimization for Variational Inference","created":"2020-09-01","cited_by_count":21},{"id":"1511.00146","title":"Faster Stochastic Variational Inference using Proximal-Gradient Methods with General Divergence Functions","created":"2015-10-31","cited_by_count":19},{"id":"2111.03144","title":"Amortized Variational Inference for Simple Hierarchical Models","created":"2021-11-04","cited_by_count":19},{"id":"2304.05527","title":"Black Box Variational Inference with a Deterministic Objective: Faster, More Accurate, and Even More Black Box","created":"2023-04-11","cited_by_count":17},{"id":"1902.00468","title":"Multilevel Monte Carlo Variational Inference","created":"2019-02-01","cited_by_count":15},{"id":"2110.01827","title":"When is the Convergence Time of Langevin Algorithms Dimension Independent? A Composite Optimization Viewpoint","created":"2021-10-05","cited_by_count":12},{"id":"1509.02866","title":"Fast Second-Order Stochastic Backpropagation for Variational Inference","created":"2015-09-09","cited_by_count":8},{"id":"2104.05886","title":"The computational asymptotics of Gaussian variational inference and the Laplace approximation","created":"2021-04-13","cited_by_count":8},{"id":"1706.02375","title":"Fast Black-box Variational Inference through Stochastic Trust-Region Optimization","created":"2017-06-07","cited_by_count":7},{"id":"1705.08931","title":"Proximity Variational Inference","created":"2017-05-24","cited_by_count":6},{"id":"2206.06295","title":"Markov Chain Score Ascent: A Unifying Framework of Variational Inference with Markovian Gradients","created":"2022-06-13","cited_by_count":6},{"id":"2303.10472","title":"Practical and Matching Gradient Variance Bounds for Black-Box Variational Bayesian Inference","created":"2023-03-18","cited_by_count":6},{"id":"2301.08297","title":"Parametrization Cookbook: A set of Bijective Parametrizations for using Machine Learning methods in Statistical Inference","created":"2023-01-19","cited_by_count":3}],"next_cursor":null}