Research map / Learning theory and algorithms / Prediction and decision losses
The Rashomon Set Has It All: Analyzing Trustworthiness of Trees under Multiplicity
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Studies how the Rashomon set of near-optimal decision trees can be exploited to select trees that satisfy multiple trustworthiness criteria beyond interpretability and fairness.
Problem
Many models fit a dataset almost equally well (the Rashomon set), and prior work used this flexibility for interpretability and fairness, but it is unclear how far it extends to other trustworthiness criteria under multiplicity.
Approach
Analyzes trustworthiness of decision trees across the full Rashomon set rather than a single optimal tree, examining whether the set contains models that are simultaneously trustworthy along several criteria.
Closest papers by meaning
- SORTeD Rashomon Sets of Sparse Decision Trees: Anytime Enumeration (NeurIPS 2025 · similarity 0.91)
- Dropout-Based Rashomon Set Exploration for Efficient Predictive Multiplicity Estimation (ICLR 2024 · similarity 0.87)
- RashomonGB: Analyzing the Rashomon Effect and Mitigating Predictive Multiplicity in Gradient Boosting (NeurIPS 2024 · similarity 0.87)
- ElliCE: Efficient and Provably Robust Algorithmic Recourse via the Rashomon Sets (NeurIPS 2025 · similarity 0.87)
- Position: Amazing Things Come From Having Many Good Models (ICML 2024 · similarity 0.86)
- Near-Optimal Decision Trees in a SPLIT Second (ICML 2025 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.