# Uncertainty in the Variational Information Bottleneck

arXiv: https://arxiv.org/abs/1807.00906 · HTML: https://mlsanity.com/paper/1807.00906/

## Key facts

- Cited by 39 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Jul 2018.

## Built on by (most cited first, 30 of 39)

- [On the Practicality of Deterministic Epistemic Uncertainty](https://mlsanity.com/paper/2107.00649/) (2021)
- [Hierarchical VAEs Know What They Don't Know](https://mlsanity.com/paper/2102.08248/) (2021)
- [Rectangular Flows for Manifold Learning](https://mlsanity.com/paper/2106.01413/) (2021)
- [DICE: Diversity in Deep Ensembles via Conditional Redundancy Adversarial Estimation](https://mlsanity.com/paper/2101.05544/) (2021)
- [On the Out-of-distribution Generalization of Probabilistic Image Modelling](https://mlsanity.com/paper/2109.02639/) (2021)
- [Random-Set Neural Networks (RS-NN)](https://mlsanity.com/paper/2307.05772/) (2023)
- [IB-UQ: Information bottleneck based uncertainty quantification for neural function regression and neural operator learning](https://mlsanity.com/paper/2302.03271/) (2023)
- [Latent Discriminant deterministic Uncertainty](https://mlsanity.com/paper/2207.10130/) (2022)
- [Bayesian Imitation Learning for End-to-End Mobile Manipulation](https://mlsanity.com/paper/2202.07600/) (2022)
- [Posterior Refinement Improves Sample Efficiency in Bayesian Neural Networks](https://mlsanity.com/paper/2205.10041/) (2022)
- [Handling Out-of-Distribution Data: A Survey](https://mlsanity.com/paper/2507.21160/) (2025)
- [GSMFlow: Generation Shifts Mitigating Flow for Generalized Zero-Shot Learning](https://mlsanity.com/paper/2207.01798/) (2022)
- [Bounds all around: training energy-based models with bidirectional bounds](https://mlsanity.com/paper/2111.00929/) (2021)
- [Forte : Finding Outliers with Representation Typicality Estimation](https://mlsanity.com/paper/2410.01322/) (2024)
- [Mitigating Hallucinations in Large Vision-Language Models by Adaptively Constraining Information Flow](https://mlsanity.com/paper/2502.20750/) (2025)
- [Epistemic Artificial Intelligence is Essential for Machine Learning Models to Truly 'Know When They Do Not Know'](https://mlsanity.com/paper/2505.04950/) (2025)
- [InfoAT: Improving Adversarial Training Using the Information Bottleneck Principle](https://mlsanity.com/paper/2206.12292/) (2022)
- [From Psychological Curiosity to Artificial Curiosity: Curiosity-Driven Learning in Artificial Intelligence Tasks](https://mlsanity.com/paper/2201.08300/) (2022)
- [Information-Theoretic Reward Modeling for Stable RLHF: Detecting and Mitigating Reward Hacking](https://mlsanity.com/paper/2510.13694/) (2025)
- [Competing Mutual Information Constraints with Stochastic Competition-based Activations for Learning Diversified Representations](https://mlsanity.com/paper/2201.03624/) (2022)
- [Planning to Go Out-of-Distribution in Offline-to-Online Reinforcement Learning](https://mlsanity.com/paper/2310.05723/) (2023)
- [Weakly-Supervised Residual Evidential Learning for Multi-Instance Uncertainty Estimation](https://mlsanity.com/paper/2405.04405/) (2024)
- [Unsupervised Class-Incremental Learning Through Confusion](https://mlsanity.com/paper/2104.04450/) (2021)
- [Deconvolutional Density Network: Modeling Free-Form Conditional Distributions](https://mlsanity.com/paper/2105.14367/) (2021)
- [Fully Heteroscedastic Count Regression with Deep Double Poisson Networks](https://mlsanity.com/paper/2406.09262/) (2024)
- [A Rate-Distortion View of Uncertainty Quantification](https://mlsanity.com/paper/2406.10775/) (2024)
- [Quantifying Model Uncertainty for Semantic Segmentation using Operators in the RKHS](https://mlsanity.com/paper/2211.01999/) (2022)
- [Discriminant Distance-Aware Representation on Deterministic Uncertainty Quantification Methods](https://mlsanity.com/paper/2402.12664/) (2024)
- [Self-Paced Uncertainty Estimation for One-shot Person Re-Identification](https://mlsanity.com/paper/2104.09152/) (2021)
- [Flexible Variational Information Bottleneck: Achieving Diverse Compression with a Single Training](https://mlsanity.com/paper/2402.01238/) (2024)

## 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.