# Dropout Strikes Back: Improved Uncertainty Estimation via Diversity Sampling

arXiv: https://arxiv.org/abs/2003.03274 · HTML: https://mlsanity.com/paper/2003.03274/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Mar 2020.

## Built on by (most cited first, 4 of 4)

- [From Risk to Uncertainty: Generating Predictive Uncertainty Measures via Bayesian Estimation](https://mlsanity.com/paper/2402.10727/) (2024)
- [Improving robustness and calibration in ensembles with diversity regularization](https://mlsanity.com/paper/2201.10908/) (2022)
- [Estimating Confidence of Predictions of Individual Classifiers and Their Ensembles for the Genre Classification Task](https://mlsanity.com/paper/2206.07427/) (2022)
- [Can Uncertainty Quantification Improve Learned Index Benefit Estimation?](https://mlsanity.com/paper/2410.17748/) (2024)

## Abstract (arXiv)

Uncertainty estimation for machine learning models is of high importance in many scenarios such as constructing the confidence intervals for model predictions and detection of out-of-distribution or adversarially generated points. In this work, we show that modifying the sampling distributions for dropout layers in neural networks improves the quality of uncertainty estimation. Our main idea consists of two main steps: computing data-driven correlations between neurons and generating samples, which include maximally diverse neurons. In a series of experiments on simulated and real-world data, we demonstrate that the diversification via determinantal point processes-based sampling achieves state-of-the-art results in uncertainty estimation for regression and classification tasks. An important feature of our approach is that it does not require any modification to the models or training procedures, allowing straightforward application to any deep learning model with dropout layers.