mlsanityData to 7 Oct 2026

Overpruning in Variational Bayesian Neural Networks

arXiv 1801.06230 ↗First posted 18 Jan 2018stat.MLcited by 21

Not on the map. Why?

Abstract (arXiv)

The motivations for using variational inference (VI) in neural networks differ significantly from those in latent variable models. This has a counter-intuitive consequence; more expressive variational approximations can provide significantly worse predictions as compared to those with less expressive families. In this work we make two contributions. First, we identify a cause of this performance gap, variational over-pruning. Second, we introduce a theoretically grounded explanation for this phenomenon. Our perspective sheds light on several related published results and provides intuition into the design of effective variational approximations of neural networks.

Key facts. Cited by 21 papers in the map (data through 7 Oct 2026). First posted on arXiv 18 Jan 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 4; 2022: 6; 2023: 4; 2024: 3; 2025: 2; 2026: 2.

21 papers.

Sort:

By area:

  1. 2021Bayesian Neural Network Priors Revisitedcited by 121
  2. 2022Do Bayesian Neural Networks Need To Be Fully Stochastic?cited by 63
  3. 2024Variational Learning is Effective for Large Deep Networkscited by 62
  4. 2023BayesDAG: Gradient-Based Posterior Inference for Causal Discoverycited by 33
  5. 2021A survey on Variational Autoencoders from a GreenAI perspectivecited by 22
  6. 2022Wide Mean-Field Bayesian Neural Networks Ignore the Datacited by 22
  7. 2022Partitioned Variational Inference: A Framework for Probabilistic Federated Learningcited by 13
  8. 2023RECOMBINER: Robust and Enhanced Compression with Bayesian Implicit Neural Representationscited by 9
  9. 2022On the detrimental effect of invariances in the likelihood for variational inferencecited by 8
  10. 2021Wide Mean-Field Variational Bayesian Neural Networks Ignore the Datacited by 7
  11. 2021TyXe: Pyro-based Bayesian neural nets for Pytorchcited by 6
  12. 2022Markov Chain Score Ascent: A Unifying Framework of Variational Inference with Markovian Gradientscited by 6
9 more
  1. 2025Variational Visual Question Answering for Uncertainty-Aware Selective Predictioncited by 5
  2. 2023Density Uncertainty Layers for Reliable Uncertainty Estimationcited by 4
  3. 2026On the Interplay of Priors and Overparametrization in Bayesian Neural Network Posteriorscited by 2
  4. 2022Enhancing variational generation through self-decompositioncited by 1
  5. 2023Leveraging Task Structures for Improved Identifiability in Neural Network Representationscited by 1
  6. 2024Temporal-Difference Variational Continual Learningcited by 1
  7. 2024BALI: Learning Neural Networks via Bayesian Layerwise Inferencecited by 1
  8. 2025Understanding the Trade-offs in Accuracy and Uncertainty Quantification: Architecture and Inference Choices in Bayesian Neural Networkscited by 0
  9. 2026Calibrated Sampling-Free Uncertainty Estimation in Bayesian Deep Learningcited by 0