# URSABench: Comprehensive Benchmarking of Approximate Bayesian Inference Methods for Deep Neural Networks

arXiv: https://arxiv.org/abs/2007.04466 · HTML: https://mlsanity.com/paper/2007.04466/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Jul 2020.

## Built on by (most cited first, 9 of 9)

- [DEUP: Direct Epistemic Uncertainty Prediction](https://mlsanity.com/paper/2102.08501/) (2021)
- [A Data-Driven Measure of Relative Uncertainty for Misclassification Detection](https://mlsanity.com/paper/2306.01710/) (2023)
- [Post-hoc loss-calibration for Bayesian neural networks](https://mlsanity.com/paper/2106.06997/) (2021)
- [Evidential Deep Learning for Uncertainty Quantification and Out-of-Distribution Detection in Jet Identification using Deep Neural Networks](https://mlsanity.com/paper/2501.05656/) (2025)
- [On Efficient Uncertainty Estimation for Resource-Constrained Mobile Applications](https://mlsanity.com/paper/2111.09838/) (2021)
- [Impact of Parameter Sparsity on Stochastic Gradient MCMC Methods for Bayesian Deep Learning](https://mlsanity.com/paper/2202.03770/) (2022)
- [Neurosymbolic Artificial Intelligence for Robust Network Intrusion Detection: From Scratch to Transfer Learning](https://mlsanity.com/paper/2506.04454/) (2025)
- [Challenges and Opportunities in Approximate Bayesian Deep Learning for Intelligent IoT Systems](https://mlsanity.com/paper/2112.01675/) (2021)
- [Streaming Bayesian Modeling for predicting Fat-Tailed Customer Lifetime Value](https://mlsanity.com/paper/2312.00373/) (2023)

## Abstract (arXiv)

While deep learning methods continue to improve in predictive accuracy on a wide range of application domains, significant issues remain with other aspects of their performance including their ability to quantify uncertainty and their robustness. Recent advances in approximate Bayesian inference hold significant promise for addressing these concerns, but the computational scalability of these methods can be problematic when applied to large-scale models. In this paper, we describe initial work on the development ofURSABench(the Uncertainty, Robustness, Scalability, and Accu-racy Benchmark), an open-source suite of bench-marking tools for comprehensive assessment of approximate Bayesian inference methods with a focus on deep learning-based classification tasks