{"total":90,"rows":[{"id":"2301.03028","title":"Generative Time Series Forecasting with Diffusion, Denoise, and Disentanglement","created":"2023-01-08","cited_by_count":90,"area":null},{"id":"2406.07423","title":"Beyond ELBOs: A Large-Scale Evaluation of Variational Methods for Sampling","created":"2024-06-11","cited_by_count":56,"area":null},{"id":"2203.04176","title":"Variational methods for simulation-based inference","created":"2022-03-08","cited_by_count":43,"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":"2112.01589","title":"InfoLM: A New Metric to Evaluate Summarization & Data2Text Generation","created":"2021-12-02","cited_by_count":33,"area":null},{"id":"2106.15980","title":"Variational Refinement for Importance Sampling Using the Forward Kullback-Leibler Divergence","created":"2021-06-30","cited_by_count":29,"area":null},{"id":"2307.01050","title":"Transport meets Variational Inference: Controlled Monte Carlo Diffusions","created":"2023-07-03","cited_by_count":21,"area":null},{"id":"2207.13177","title":"Sliced Wasserstein Variational Inference","created":"2022-07-26","cited_by_count":18,"area":null},{"id":"2306.01122","title":"On the Convergence of Coordinate Ascent Variational Inference","created":"2023-06-01","cited_by_count":18,"area":null},{"id":"2312.01133","title":"$t^3$-Variational Autoencoder: Learning Heavy-tailed Data with Student's t and Power Divergence","created":"2023-12-02","cited_by_count":18,"area":null},{"id":"2209.10888","title":"Amortized Variational Inference: A Systematic Review","created":"2022-09-22","cited_by_count":16,"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":"2101.07046","title":"Mind the Gap when Conditioning Amortised Inference in Sequential Latent-Variable Models","created":"2021-01-18","cited_by_count":14,"area":null},{"id":"2202.10951","title":"Multiple Importance Sampling ELBO and Deep Ensembles of Variational Approximations","created":"2022-02-22","cited_by_count":12,"area":null},{"id":"2104.00241","title":"Variational Inference MPC using Tsallis Divergence","created":"2021-04-01","cited_by_count":11,"area":null},{"id":"2110.10422","title":"PriorVAE: Encoding spatial priors with VAEs for small-area estimation","created":"2021-10-20","cited_by_count":11,"area":null},{"id":"2205.07918","title":"Fat-Tailed Variational Inference with Anisotropic Tail Adaptive Flows","created":"2022-05-16","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":"2410.02596","title":"Beyond Squared Error: Exploring Loss Design for Enhanced Training of Generative Flow Networks","created":"2024-10-03","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":"2501.18537","title":"Loss Functions and Operators Generated by f-Divergences","created":"2025-01-30","cited_by_count":10,"area":null},{"id":"2305.16446","title":"The Representation Jensen-Shannon Divergence","created":"2023-05-25","cited_by_count":9,"area":null},{"id":"2410.11067","title":"Variational Inference in Location-Scale Families: Exact Recovery of the Mean and Correlation Matrix","created":"2024-10-14","cited_by_count":9,"area":null},{"id":"2111.01750","title":"Spiking Generative Adversarial Networks With a Neural Network Discriminator: Local Training, Bayesian Models, and Continual Meta-Learning","created":"2021-11-02","cited_by_count":8,"area":null},{"id":"2208.06270","title":"RenyiCL: Contrastive Representation Learning with Skew Renyi Divergence","created":"2022-08-12","cited_by_count":8,"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":"2111.00780","title":"Pseudo-Spherical Contrastive Divergence","created":"2021-11-01","cited_by_count":7,"area":null},{"id":"2210.04974","title":"Function-space regularized R\\'enyi divergences","created":"2022-10-10","cited_by_count":7,"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":"2107.05438","title":"Bayesian brains and the R\\'enyi divergence","created":"2021-07-12","cited_by_count":6,"area":null},{"id":"2203.01859","title":"Robust PAC$^m$: Training Ensemble Models Under Misspecification and Outliers","created":"2022-03-03","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":"2206.09453","title":"Bounding Evidence and Estimating Log-Likelihood in VAE","created":"2022-06-19","cited_by_count":6,"area":null},{"id":"2209.11366","title":"Jensen-Shannon Divergence Based Novel Loss Functions for Bayesian Neural Networks","created":"2022-09-23","cited_by_count":6,"area":null},{"id":"2410.09355","title":"On Divergence Measures for Training GFlowNets","created":"2024-10-12","cited_by_count":6,"area":null},{"id":"2103.05684","title":"Monotonic Alpha-divergence Minimisation for Variational Inference","created":"2021-03-09","cited_by_count":5,"area":null},{"id":"2304.11251","title":"Machine Learning and the Future of Bayesian Computation","created":"2023-04-21","cited_by_count":4,"area":null},{"id":"2408.00681","title":"Alpha-VI DeepONet: A prior-robust variational Bayesian approach for enhancing DeepONets with uncertainty quantification","created":"2024-08-01","cited_by_count":4,"area":null},{"id":"2103.01030","title":"An Easy to Interpret Diagnostic for Approximate Inference: Symmetric Divergence Over Simulations","created":"2021-02-25","cited_by_count":3,"area":null},{"id":"2111.02947","title":"Variational Inference with Holder Bounds","created":"2021-11-04","cited_by_count":3,"area":null},{"id":"2112.04583","title":"Computing Divergences between Discrete Decomposable Models","created":"2021-12-08","cited_by_count":3,"area":null},{"id":"2203.04950","title":"Renyi Fair Information Bottleneck for Image Classification","created":"2022-03-09","cited_by_count":3,"area":null},{"id":"2310.16653","title":"Adaptive importance sampling for heavy-tailed distributions via $\\alpha$-divergence minimization","created":"2023-10-25","cited_by_count":3,"area":null},{"id":"2511.01064","title":"Generalized Guarantees for Variational Inference in the Presence of Even and Elliptical Symmetry","created":"2025-11-02","cited_by_count":3,"area":null},{"id":"2111.13027","title":"Toward an Idiomatic Framework for Cognitive Robotics","created":"2021-11-25","cited_by_count":2,"area":null},{"id":"2201.12955","title":"Optimal Regret Is Achievable with Bounded Approximate Inference Error: An Enhanced Bayesian Upper Confidence Bound Framework","created":"2022-01-31","cited_by_count":2,"area":null},{"id":"2202.00187","title":"Deep Reference Priors: What is the best way to pretrain a model?","created":"2022-02-01","cited_by_count":2,"area":null},{"id":"2209.05732","title":"R\\'{e}nyi Divergence Deep Mutual Learning","created":"2022-09-13","cited_by_count":2,"area":null},{"id":"2405.14840","title":"Differentiable Annealed Importance Sampling Minimizes The Symmetrized Kullback-Leibler Divergence Between Initial and Target Distribution","created":"2024-05-23","cited_by_count":2,"area":null},{"id":"2505.10466","title":"FlowVAT: Normalizing Flow Variational Inference with Affine-Invariant Tempering","created":"2025-05-15","cited_by_count":2,"area":null},{"id":"2109.11737","title":"Estimating R\\'enyi's $\\alpha$-Cross-Entropies in a Matrix-Based Way","created":"2021-09-24","cited_by_count":1,"area":null},{"id":"2206.10043","title":"Classification Utility, Fairness, and Compactness via Tunable Information Bottleneck and R\\'enyi Measures","created":"2022-06-20","cited_by_count":1,"area":null},{"id":"2209.03077","title":"On the Equality of the ELBO to a Sum of Entropies at Stationary Points of Learning","created":"2022-09-07","cited_by_count":1,"area":null},{"id":"2301.11476","title":"Generalized Munchausen Reinforcement Learning using Tsallis KL Divergence","created":"2023-01-27","cited_by_count":1,"area":null},{"id":"2302.06035","title":"Variational Bayesian Neural Networks via Resolution of Singularities","created":"2023-02-13","cited_by_count":1,"area":null},{"id":"2305.15927","title":"Parameter Estimation in DAGs from Incomplete Data via Optimal Transport","created":"2023-05-25","cited_by_count":1,"area":null},{"id":"2307.11249","title":"On the Natural Gradient of the Evidence Lower Bound","created":"2023-07-20","cited_by_count":1,"area":null},{"id":"2405.15991","title":"R\\'enyi Neural Processes","created":"2024-05-25","cited_by_count":1,"area":null},{"id":"2407.08843","title":"Inflationary Flows: Calibrated Bayesian Inference with Diffusion-Based Models","created":"2024-07-11","cited_by_count":1,"area":null},{"id":"2407.15687","title":"SoftCVI: Contrastive variational inference with self-generated soft labels","created":"2024-07-22","cited_by_count":1,"area":null},{"id":"2502.09591","title":"Censor Dependent Variational Inference","created":"2025-02-13","cited_by_count":1,"area":null},{"id":"2502.10295","title":"Fenchel-Young Variational Learning","created":"2025-02-14","cited_by_count":1,"area":null},{"id":"2502.18300","title":"Bayesian Computation in Deep Learning","created":"2025-02-25","cited_by_count":1,"area":null},{"id":"2504.10004","title":"An Image is Worth $K$ Topics: A Visual Structural Topic Model with Pretrained Image Embeddings","created":"2025-04-14","cited_by_count":1,"area":null},{"id":"2504.21634","title":"Quantitative Auditing of AI Fairness with Differentially Private Synthetic Data","created":"2025-04-30","cited_by_count":1,"area":null},{"id":"2507.14652","title":"Accelerating Hamiltonian Monte Carlo for Bayesian Inference in Neural Networks and Neural Operators","created":"2025-07-19","cited_by_count":1,"area":null},{"id":"2511.21223","title":"Maxitive Donsker-Varadhan Formulation for Possibilistic Variational Inference","created":"2025-11-26","cited_by_count":1,"area":null},{"id":"2602.21269","title":"Group Orthogonalized Policy Optimization:Group Policy Optimization as Orthogonal Projection in Hilbert Space","created":"2026-02-24","cited_by_count":1,"area":null},{"id":"2604.18310","title":"Symmetry Guarantees Statistic Recovery in Variational Inference","created":"2026-04-20","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":"2110.05794","title":"Information Theoretic Structured Generative Modeling","created":"2021-10-12","cited_by_count":0,"area":null},{"id":"2112.01675","title":"Challenges and Opportunities in Approximate Bayesian Deep Learning for Intelligent IoT Systems","created":"2021-12-03","cited_by_count":0,"area":null},{"id":"2303.04450","title":"Nonlinear Kalman Filtering with Reparametrization Gradients","created":"2023-03-08","cited_by_count":0,"area":null},{"id":"2403.08941","title":"Towards Model-Agnostic Posterior Approximation for Fast and Accurate Variational Autoencoders","created":"2024-03-13","cited_by_count":0,"area":null},{"id":"2406.14071","title":"Bayesian Bandit Algorithms with Approximate Inference in Stochastic Linear Bandits","created":"2024-06-20","cited_by_count":0,"area":null},{"id":"2503.17355","title":"Glivenko-Cantelli for $f$-divergence","created":"2025-03-21","cited_by_count":0,"area":null},{"id":"2509.20574","title":"The Sensitivity of Variational Bayesian Neural Network Performance to Hyperparameters","created":"2025-09-24","cited_by_count":0,"area":null},{"id":"2510.03109","title":"Rates of Convergence of Generalised Variational Inference Posteriors under Prior Misspecification","created":"2025-10-03","cited_by_count":0,"area":null},{"id":"2511.13621","title":"Alpha Divergence Losses for Biometric Verification","created":"2025-11-17","cited_by_count":0,"area":null},{"id":"2511.15409","title":"Recursive Entropic Variational Inference for Nonlinear State-Space Models","created":"2025-11-19","cited_by_count":0,"area":null},{"id":"2602.04272","title":"Bures-Wasserstein Importance-Weighted Evidence Lower Bound: Exposition and Applications","created":"2026-02-04","cited_by_count":0,"area":null},{"id":"2602.04555","title":"Finding Structure in Continual Learning","created":"2026-02-04","cited_by_count":0,"area":null},{"id":"2602.06627","title":"Trust Regions Sell, But Who's Buying? Overlap Geometry as an Alternative Trust Region for Policy Optimization","created":"2026-02-06","cited_by_count":0,"area":null},{"id":"2603.27488","title":"Variational Learning of Fractional Posteriors","created":"2026-03-29","cited_by_count":0,"area":null},{"id":"2604.25984","title":"Occam's Razor is Only as Sharp as Your ELBO","created":"2026-04-28","cited_by_count":0,"area":null},{"id":"2605.27747","title":"Soft Specialists: $\\alpha$-R\\'enyi Ensembles for Uncertainty-Aware LLM Post-Training","created":"2026-05-26","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},{"id":"2606.15479","title":"Bayesian 3D Steerable CNNs: Enabling Equivariance and Uncertainty Quantification Simultaneously","created":"2026-06-13","cited_by_count":0,"area":null},{"id":"2606.31664","title":"Sparsity-Inducing Divergence Losses for Biometric Verification","created":"2026-06-30","cited_by_count":0,"area":null},{"id":"2609.29546","title":"Generalized Graph Variational Autoencoders: Bounded Divergences Control Posterior Collapse","created":"2026-08-25","cited_by_count":0,"area":null}],"next_cursor":null}