# Dropout-Based Rashomon Set Exploration for Efficient Predictive Multiplicity Estimation

arXiv: https://arxiv.org/abs/2402.00728 · HTML: https://mlsanity.com/paper/2402.00728/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 54 references that are in the map.
- First posted on arXiv 1 Feb 2024.

## Builds on (most cited first, 24 of 24)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [YOLOv3: An Incremental Improvement](https://mlsanity.com/paper/1804.02767/) (2018)
- [MMDetection: Open MMLab Detection Toolbox and Benchmark](https://mlsanity.com/paper/1906.07155/) (2019)
- [How transferable are features in deep neural networks?](https://mlsanity.com/paper/1411.1792/) (2014)
- [Model Cards for Model Reporting](https://mlsanity.com/paper/1810.03993/) (2018)
- [Deep Neural Networks as Gaussian Processes](https://mlsanity.com/paper/1711.00165/) (2017)
- [Underspecification Presents Challenges for Credibility in Modern Machine Learning](https://mlsanity.com/paper/2011.03395/) (2020)
- [Variational Dropout and the Local Reparameterization Trick](https://mlsanity.com/paper/1506.02557/) (2015)
- [Lipschitz regularity of deep neural networks: analysis and efficient estimation](https://mlsanity.com/paper/1805.10965/) (2018)
- [Predictive Multiplicity in Classification](https://mlsanity.com/paper/1909.06677/) (2019)
- [Exploring the Whole Rashomon Set of Sparse Decision Trees](https://mlsanity.com/paper/2209.08040/) (2022)
- [Characterizing Fairness Over the Set of Good Models Under Selective Labels](https://mlsanity.com/paper/2101.00352/) (2021)
- [Generalization Error Bounds of Gradient Descent for Learning Over-parameterized Deep ReLU Networks](https://mlsanity.com/paper/1902.01384/) (2019)
- [Rashomon Capacity: A Metric for Predictive Multiplicity in Classification](https://mlsanity.com/paper/2206.01295/) (2022)
- [Survey of Dropout Methods for Deep Neural Networks](https://mlsanity.com/paper/1904.13310/) (2019)
- [Predictive Multiplicity in Probabilistic Classification](https://mlsanity.com/paper/2206.01131/) (2022)
- [Predicting is not Understanding: Recognizing and Addressing Underspecification in Machine Learning](https://mlsanity.com/paper/2207.02598/) (2022)
- [Arbitrary Decisions are a Hidden Cost of Differentially Private Training](https://mlsanity.com/paper/2302.14517/) (2023)
- [Reconciling Individual Probability Forecasts](https://mlsanity.com/paper/2209.01687/) (2022)
- [Arbitrariness Lies Beyond the Fairness-Accuracy Frontier](https://mlsanity.com/paper/2306.09425/) (2023)

## Built on by (most cited first, 18 of 18)

- [Systemizing Multiplicity: The Curious Case of Arbitrariness in Machine Learning](https://mlsanity.com/paper/2501.14959/) (2025)
- [An Experimental Study on the Rashomon Effect of Balancing Methods in Imbalanced Classification](https://mlsanity.com/paper/2405.01557/) (2024)
- [Quantifying Prediction Consistency Under Fine-Tuning Multiplicity in Tabular LLMs](https://mlsanity.com/paper/2407.04173/) (2024)
- [The Role of Hyperparameters in Predictive Multiplicity](https://mlsanity.com/paper/2503.13506/) (2025)
- [ElliCE: Efficient and Provably Robust Algorithmic Recourse via the Rashomon Sets](https://mlsanity.com/paper/2602.07674/) (2026)
- [Using predictive multiplicity to measure individual performance within the AI Act](https://mlsanity.com/paper/2602.11944/) (2026)
- [Argumentative Ensembling for Robust Recourse under Model Multiplicity](https://mlsanity.com/paper/2506.20260/) (2025)
- [Parameter-Efficient Construction of the Rashomon Slice for Concept Bottleneck Models](https://mlsanity.com/paper/2511.19636/) (2025)
- [DIVERSE: Disagreement-Inducing Vector Evolution for Rashomon Set Exploration](https://mlsanity.com/paper/2601.20627/) (2026)
- [CASHomon Sets: Efficient Rashomon Sets Across Multiple Model Classes and their Hyperparameters](https://mlsanity.com/paper/2603.15321/) (2026)
- [Efficient & Correct Predictive Equivalence for Decision Trees](https://mlsanity.com/paper/2509.17774/) (2025)
- [Data as a Lever: A Neighbouring Datasets Perspective on Predictive Multiplicity](https://mlsanity.com/paper/2510.21303/) (2025)
- [The Double-Edged Nature of the Rashomon Set for Trustworthy Machine Learning](https://mlsanity.com/paper/2511.21799/) (2025)
- [Rashomon Sets and Model Multiplicity in Federated Learning](https://mlsanity.com/paper/2602.09520/) (2026)
- [Model Multiplicity and Predictive Arbitrariness in Recidivism Risk Assessment](https://mlsanity.com/paper/2606.02198/) (2026)
- [Model Stealing Through the Lens of Model Multiplicity](https://mlsanity.com/paper/2606.15493/) (2026)
- [AVCG: A Generalized Variational Framework for Counterfactual Generation under Hypothesis Distributions](https://mlsanity.com/paper/2609.07917/) (2026)
- [Does Model Uncertainty Track Human Ambiguity? Evidence from Multi-Annotator Vision Benchmarks](https://mlsanity.com/paper/2609.34506/) (2026)

## Abstract (arXiv)

Predictive multiplicity refers to the phenomenon in which classification tasks may admit multiple competing models that achieve almost-equally-optimal performance, yet generate conflicting outputs for individual samples. This presents significant concerns, as it can potentially result in systemic exclusion, inexplicable discrimination, and unfairness in practical applications. Measuring and mitigating predictive multiplicity, however, is computationally challenging due to the need to explore all such almost-equally-optimal models, known as the Rashomon set, in potentially huge hypothesis spaces. To address this challenge, we propose a novel framework that utilizes dropout techniques for exploring models in the Rashomon set. We provide rigorous theoretical derivations to connect the dropout parameters to properties of the Rashomon set, and empirically evaluate our framework through extensive experimentation. Numerical results show that our technique consistently outperforms baselines in terms of the effectiveness of predictive multiplicity metric estimation, with runtime speedup up to 20× ~ 5000×. With efficient Rashomon set exploration and metric estimation, mitigation of predictive multiplicity is then achieved through dropout ensemble and model selection.