mlsanityData to 7 Oct 2026

Uncertainty in the Variational Information Bottleneck

arXiv 1807.00906 ↗First posted 2 Jul 2018cs.LG stat.MLcited by 39

Not on the map. Why?

Abstract (arXiv)

We present a simple case study, demonstrating that Variational Information Bottleneck (VIB) can improve a network's classification calibration as well as its ability to detect out-of-distribution data. Without explicitly being designed to do so, VIB gives two natural metrics for handling and quantifying uncertainty.

Key facts. Cited by 39 papers in the map (data through 7 Oct 2026). First posted on arXiv 2 Jul 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 12; 2022: 8; 2023: 3; 2024: 9; 2025: 6; 2026: 1.

39 papers.

Sort:

By area:

  1. 2021On the Practicality of Deterministic Epistemic Uncertaintycited by 62
  2. 2021Hierarchical VAEs Know What They Don't Knowcited by 58
  3. 2021Rectangular Flows for Manifold Learningcited by 49
  4. 2021DICE: Diversity in Deep Ensembles via Conditional Redundancy Adversarial Estimationcited by 48
  5. 2021On the Out-of-distribution Generalization of Probabilistic Image Modellingcited by 32
  6. 2023Random-Set Neural Networks (RS-NN)cited by 19
  7. 2023IB-UQ: Information bottleneck based uncertainty quantification for neural function regression and neural operator learningcited by 18
  8. 2022Latent Discriminant deterministic Uncertaintycited by 17
  9. 2022Posterior Refinement Improves Sample Efficiency in Bayesian Neural Networkscited by 14
  10. 2025Handling Out-of-Distribution Data: A Surveycited by 14
  11. 2022Bayesian Imitation Learning for End-to-End Mobile Manipulationcited by 13
  12. 2022GSMFlow: Generation Shifts Mitigating Flow for Generalized Zero-Shot Learningcited by 12
27 more
  1. 2021Bounds all around: training energy-based models with bidirectional boundscited by 10
  2. 2024Forte : Finding Outliers with Representation Typicality Estimationcited by 9
  3. 2025Mitigating Hallucinations in Large Vision-Language Models by Adaptively Constraining Information Flowcited by 9
  4. 2025Epistemic Artificial Intelligence is Essential for Machine Learning Models to Truly 'Know When They Do Not Know'cited by 8
  5. 2022InfoAT: Improving Adversarial Training Using the Information Bottleneck Principlecited by 7
  6. 2022From Psychological Curiosity to Artificial Curiosity: Curiosity-Driven Learning in Artificial Intelligence Taskscited by 6
  7. 2025Information-Theoretic Reward Modeling for Stable RLHF: Detecting and Mitigating Reward Hackingcited by 5
  8. 2022Competing Mutual Information Constraints with Stochastic Competition-based Activations for Learning Diversified Representationscited by 4
  9. 2023Planning to Go Out-of-Distribution in Offline-to-Online Reinforcement Learningcited by 4
  10. 2024Weakly-Supervised Residual Evidential Learning for Multi-Instance Uncertainty Estimationcited by 4
  11. 2021Unsupervised Class-Incremental Learning Through Confusioncited by 3
  12. 2021Deconvolutional Density Network: Modeling Free-Form Conditional Distributionscited by 3
  13. 2024Fully Heteroscedastic Count Regression with Deep Double Poisson Networkscited by 3
  14. 2024A Rate-Distortion View of Uncertainty Quantificationcited by 3
  15. 2022Quantifying Model Uncertainty for Semantic Segmentation using Operators in the RKHScited by 2
  16. 2024Discriminant Distance-Aware Representation on Deterministic Uncertainty Quantification Methodscited by 2
  17. 2021Self-Paced Uncertainty Estimation for One-shot Person Re-Identificationcited by 1
  18. 2024Flexible Variational Information Bottleneck: Achieving Diverse Compression with a Single Trainingcited by 1
  19. 2024Masked Gamma-SSL: Learning Uncertainty Estimation via Masked Image Modelingcited by 1
  20. 2026What Information Matters? Graph Out-of-Distribution Detection via Tri-Component Information Decompositioncited by 1
  21. 2021DOI: Divergence-based Out-of-Distribution Indicators via Deep Generative Modelscited by 0
  22. 2021Information Theoretic Structured Generative Modelingcited by 0
  23. 2021The Exponentially Tilted Gaussian Prior for Variational Autoencoderscited by 0
  24. 2024Cell Variational Information Bottleneck Networkcited by 0
  25. 2024Resultant: Incremental Effectiveness on Likelihood for Unsupervised Out-of-Distribution Detectioncited by 0
  26. 2025Exploring bidirectional bounds for minimax-training of Energy-based modelscited by 0
  27. 2025Label Smoothing is a Pragmatic Information Bottleneckcited by 0