DeepAI AI Chat
Log In Sign Up

Reliable Prediction Intervals with Directly Optimized Inductive Conformal Regression for Deep Learning

02/02/2023
by   Haocheng Lei, et al.
The University of Nottingham Ningbo China
0

By generating prediction intervals (PIs) to quantify the uncertainty of each prediction in deep learning regression, the risk of wrong predictions can be effectively controlled. High-quality PIs need to be as narrow as possible, whilst covering a preset proportion of real labels. At present, many approaches to improve the quality of PIs can effectively reduce the width of PIs, but they do not ensure that enough real labels are captured. Inductive Conformal Predictor (ICP) is an algorithm that can generate effective PIs which is theoretically guaranteed to cover a preset proportion of data. However, typically ICP is not directly optimized to yield minimal PI width. However, in this study, we use Directly Optimized Inductive Conformal Regression (DOICR) that takes only the average width of PIs as the loss function and increases the quality of PIs through an optimized scheme under the validity condition that sufficient real labels are captured in the PIs. Benchmark experiments show that DOICR outperforms current state-of-the-art algorithms for regression problems using underlying Deep Neural Network structures for both tabular and image data.

READ FULL TEXT

page 1

page 2

page 3

page 4

02/20/2018

High-Quality Prediction Intervals for Deep Learning: A Distribution-Free, Ensembled Approach

Deep neural networks are a powerful technique for learning complex funct...
12/13/2022

Dual Accuracy-Quality-Driven Neural Network for Prediction Interval Generation

Accurate uncertainty quantification is necessary to enhance the reliabil...
06/09/2020

PIVEN: A Deep Neural Network for Prediction Intervals with Specific Value Prediction

Improving the robustness of neural nets in regression tasks is key to th...
02/19/2022

Accurate Prediction and Uncertainty Estimation using Decoupled Prediction Interval Networks

We propose a network architecture capable of reliably estimating uncerta...
04/06/2023

Conformal Regression in Calorie Prediction for Team Jumbo-Visma

UCI WorldTour races, the premier men's elite road cycling tour, are grue...