ConfEviSurrogate: A Conformalized Evidential Surrogate Model for Uncertainty Quantification

2025-04-03

AI Summary

Uncertainty quantification for surrogate models in scientific simulation faces three key challenges: difficulty distinguishing simulation noise from model error, lack of theoretical coverage guarantees for prediction intervals, and high computational cost and weak error-decoupling capability of existing methods (e.g., Monte Carlo Dropout). This paper proposes a novel surrogate framework integrating evidential deep learning with conformal prediction—marking the first approach to jointly embed evidential distribution learning and conformal calibration. Specifically, an evidential neural network models higher-order uncertainty to explicitly disentangle multi-source errors, while conformal prediction delivers statistically rigorous, coverage-guaranteed prediction intervals. Evaluated on cosmological, ocean dynamical, and fluid dynamic simulation tasks, the method significantly improves both point prediction accuracy and interval calibration, achieves exact nominal coverage, and maintains computational efficiency and scalability.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Reasoning under Uncertainty: Uncertainty Representations
• Search and Optimization: Sampling/Simulation-based Search

Application Category

• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs

Abstract

Surrogate models, crucial for approximating complex simulation data across sciences, inherently carry uncertainties that range from simulation noise to model prediction errors. Without rigorous uncertainty quantification, predictions become unreliable and hence hinder analysis. While methods like Monte Carlo dropout and ensemble models exist, they are often costly, fail to isolate uncertainty types, and lack guaranteed coverage in prediction intervals. To address this, we introduce ConfEviSurrogate, a novel Conformalized Evidential Surrogate Model that can efficiently learn high-order evidential distributions, directly predict simulation outcomes, separate uncertainty sources, and provide prediction intervals. A conformal prediction-based calibration step further enhances interval reliability to ensure coverage and improve efficiency. Our ConfEviSurrogate demonstrates accurate predictions and robust uncertainty estimates in diverse simulations, including cosmology, ocean dynamics, and fluid dynamics.

Problem

• Quantify uncertainties in surrogate models for reliable predictions
• Isolate and manage different types of uncertainty sources
• Provide guaranteed coverage in prediction intervals efficiently

Innovation

• Conformalized Evidential Surrogate Model
• Separates uncertainty sources efficiently
• Ensures reliable prediction intervals coverage