Robust Uncertainty Quantification Using Conformalised Monte Carlo Prediction

TL;DR

MC-CP is introduced, a novel hybrid UQ method that combines a new adaptive Monte Carlo (MC) dropout method with conformal prediction (CP), enabling predictions to be consumed by CP, yielding robust prediction sets/intervals.

Abstract

Deploying deep learning models in safety-critical applications remains a very challenging task, mandating the provision of assurances for the dependable operation of these models. Uncertainty quantification (UQ) methods estimate the model's confidence per prediction, informing decision-making by considering the effect of randomness and model misspecification. Despite the advances of state-of-the-art UQ methods, they are computationally expensive or produce conservative prediction sets/intervals. We introduce MC-CP, a novel hybrid UQ method that combines a new adaptive Monte Carlo (MC) dropout method with conformal prediction (CP). MC-CP adaptively modulates the traditional MC dropout at runtime to save memory and computation resources, enabling predictions to be consumed by CP, yielding robust prediction sets/intervals. Throughout comprehensive experiments, we show that MC-CP delivers significant improvements over advanced UQ methods, like MC dropout, RAPS and CQR, both in classification and regression benchmarks. MC-CP can be easily added to existing models, making its deployment simple.

Figures (6)

• Figure 1: High-level overview of our MC-CP method for image classification.
• Figure 2: Percentage and accuracy of singleton and mixed predictions for Naive CP, RAPS, MC-CP on CIFAR-10.
• Figure 3: Mean confidence of top predictions for Naive CP, RAPS, MC-CP on CIFAR-10, CIFAR-100, Tiny ImageNet.
• Figure 4: Convergence of variance for each class during the Adaptive MC Dropout procedure.
• Figure 5: Predicted quantiles (95%, 5%) of all four methods on a sample of the Boston Housing dataset.