mlsanityData to 14 Oct 2026

Black-box α-divergence Minimization

arXiv 1511.03243 ↗First posted 10 Nov 2015stat.MLcited by 37

Not on the map. Why?

Abstract (arXiv)

Black-box alpha (BB-α) is a new approximate inference method based on the minimization of α-divergences. BB-α scales to large datasets because it can be implemented using stochastic gradient descent. BB-α can be applied to complex probabilistic models with little effort since it only requires as input the likelihood function and its gradients. These gradients can be easily obtained using automatic differentiation. By changing the divergence parameter α, the method is able to interpolate between variational Bayes (VB) (α rightarrow 0) and an algorithm similar to expectation propagation (EP) (α = 1). Experiments on probit regression and neural network regression and classification problems show that BB-α with non-standard settings of α, such as α = 0.5, usually produces better predictions than with α rightarrow 0 (VB) or α = 1 (EP).

Key facts. Cited by 37 papers in the map (data through 14 Oct 2026). First posted on arXiv 10 Nov 2015.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 2; 2022: 7; 2023: 8; 2024: 7; 2025: 3; 2026: 10.

37 papers.

Sort:

By area:

  1. 2022GFlowNets and variational inferencecited by 106
  2. 2022Confidence May Cheat: Self-Training on Graph Neural Networks under Distribution Shiftcited by 38
  3. 2021Challenges and Opportunities in High-dimensional Variational Inferencecited by 35
  4. 2022Adapting the Linearised Laplace Model Evidence for Modern Deep Learningcited by 29
  5. 2023On the Convergence of Black-Box Variational Inferencecited by 22
  6. 2023Transport meets Variational Inference: Controlled Monte Carlo Diffusionscited by 21
  7. 2024Variational Inference for Uncertainty Quantification: an Analysis of Trade-offscited by 11
  8. 2024Calib3D: Calibrating Model Preferences for Reliable 3D Scene Understandingcited by 11
  9. 2022Deep Variational Implicit Processescited by 8
  10. 2025U4D: Uncertainty-Aware 4D World Modeling from LiDAR Sequencescited by 7
  11. 2022Markov Chain Score Ascent: A Unifying Framework of Variational Inference with Markovian Gradientscited by 6
  12. 2024Bayesian neural networks for predicting uncertainty in full-field material responsecited by 5
25 more
  1. 2023Forward chi2 Divergence Based Variational Importance Samplingcited by 4
  2. 2021Variational Inference with Holder Boundscited by 3
  3. 2023Adaptive importance sampling for heavy-tailed distributions via α-divergence minimizationcited by 3
  4. 2026Hellinger Multimodal Variational Autoencoderscited by 3
  5. 2022Optimal Regret Is Achievable with Bounded Approximate Inference Error: An Enhanced Bayesian Upper Confidence Bound Frameworkcited by 2
  6. 2024Differentiable Annealed Importance Sampling Minimizes The Symmetrized Kullback-Leibler Divergence Between Initial and Target Distributioncited by 2
  7. 2024Fixed-Mean Gaussian Processes for Post-hoc Bayesian Deep Learningcited by 2
  8. 2026Amortized Simulation-Based Inference in Generalized Bayes via Neural Posterior Estimationcited by 2
  9. 2022Correcting Model Bias with Sparse Implicit Processescited by 1
  10. 2023Variational Bayesian Neural Networks via Resolution of Singularitiescited by 1
  11. 2023Parameter Estimation in DAGs from Incomplete Data via Optimal Transportcited by 1
  12. 2024Alpha-divergence loss function for neural density ratio estimationcited by 1
  13. 2024Alpha Entropy Search for New Information-based Bayesian Optimizationcited by 1
  14. 2026Symmetry Guarantees Statistic Recovery in Variational Inferencecited by 1
  15. 2026Flow-Transformed Implicit Processes for Function-Space Variational Inferencecited by 1
  16. 2023Nonlinear Kalman Filtering with Reparametrization Gradientscited by 0
  17. 2023Learning variational autoencoders via MCMC speed measurescited by 0
  18. 2025Stability-based Generalization Bounds for Variational Inferencecited by 0
  19. 2025Sparse Gaussian Processes: Structured Approximations and Power-EP Revisitedcited by 0
  20. 2026REDistill: Robust Estimator Distillation for Balancing Robustness and Efficiencycited by 0
  21. 2026Surprisal-R'enyi Free Energycited by 0
  22. 2026Beliefs Beyond Posteriors: The Predictive Cost of ELBO Bindingcited by 0
  23. 2026Soft Specialists: α-R'enyi Ensembles for Uncertainty-Aware LLM Post-Trainingcited by 0
  24. 2026Large-scale empirical tuning and comparison of default optimizers for variational inferencecited by 0
  25. 2026H"older++: Improving the Quality-Coherence Trade-off in Multimodal VAEscited by 0