{"total":21,"rows":[{"id":"2110.11216","title":"User-friendly introduction to PAC-Bayes bounds","created":"2021-10-21","cited_by_count":239,"area":null},{"id":"2103.01085","title":"Challenges and Opportunities in High-dimensional Variational Inference","created":"2021-03-01","cited_by_count":35,"area":null},{"id":"2207.08219","title":"Gradients should stay on Path: Better Estimators of the Reverse- and Forward KL Divergence for Normalizing Flows","created":"2022-07-17","cited_by_count":23,"area":null},{"id":"2210.06226","title":"Alpha-divergence Variational Inference Meets Importance Weighted Auto-Encoders: Methodology and Asymptotics","created":"2022-10-12","cited_by_count":15,"area":null},{"id":"2206.09016","title":"Path-Gradient Estimators for Continuous Normalizing Flows","created":"2022-06-17","cited_by_count":11,"area":null},{"id":"2403.13748","title":"Variational Inference for Uncertainty Quantification: an Analysis of Trade-offs","created":"2024-03-20","cited_by_count":11,"area":null},{"id":"2105.06587","title":"Empirical Evaluation of Biased Methods for Alpha Divergence Minimization","created":"2021-05-13","cited_by_count":10,"area":null},{"id":"2307.14642","title":"Linear Convergence of Black-Box Variational Inference: Should We Stick the Landing?","created":"2023-07-27","cited_by_count":10,"area":null},{"id":"2310.20090","title":"Bridging the Gap Between Variational Inference and Wasserstein Gradient Flows","created":"2023-10-31","cited_by_count":8,"area":null},{"id":"2106.05114","title":"Mixture weights optimisation for Alpha-Divergence Variational Inference","created":"2021-06-09","cited_by_count":6,"area":null},{"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,"area":null},{"id":"2403.15881","title":"Fast and Unified Path Gradient Estimators for Normalizing Flows","created":"2024-03-23","cited_by_count":5,"area":null},{"id":"2412.08824","title":"Disentangling impact of capacity, objective, batchsize, estimators, and step-size on flow VI","created":"2024-12-11","cited_by_count":5,"area":null},{"id":"2311.02516","title":"Forward $\\chi^2$ Divergence Based Variational Importance Sampling","created":"2023-11-04","cited_by_count":4,"area":null},{"id":"2402.02041","title":"Alpha-divergence loss function for neural density ratio estimation","created":"2024-02-03","cited_by_count":1,"area":null},{"id":"2405.19747","title":"Understanding and mitigating difficulties in posterior predictive evaluation","created":"2024-05-30","cited_by_count":1,"area":null},{"id":"2604.21407","title":"Even More Guarantees for Variational Inference in the Presence of Symmetries","created":"2026-04-23","cited_by_count":1,"area":null},{"id":"2308.13731","title":"Learning variational autoencoders via MCMC speed measures","created":"2023-08-26","cited_by_count":0,"area":null},{"id":"2602.18718","title":"Stochastic Gradient Variational Inference with Price's Gradient Estimator from Bures-Wasserstein to Parameter Space","created":"2026-02-21","cited_by_count":0,"area":null},{"id":"2603.15055","title":"Spatio-temporal probabilistic forecast using MMAF-guided learning","created":"2026-03-16","cited_by_count":0,"area":null},{"id":"2606.07841","title":"Large-scale empirical tuning and comparison of default optimizers for variational inference","created":"2026-06-05","cited_by_count":0,"area":null}],"next_cursor":null}