Published on Fri Sep 20 2019

Computing Full Conformal Prediction Set with Approximate Homotopy

Eugene Ndiaye, Ichiro Takeuchi

Conformal prediction methods provide an elegant framework for answering such question. Conformal set is impractical to compute exactly for many regression problems. We propose efficient algorithms to compute conformal prediction set using approximated solution of regularized empirical risk minimization.

0
0
0
Abstract

If you are predicting the label of a new object with , how confident are you that ? Conformal prediction methods provide an elegant framework for answering such question by building a $100 (1 - \alpha)\%$ confidence region without assumptions on the distribution of the data. It is based on a refitting procedure that parses all the possibilities for to select the most likely ones. Although providing strong coverage guarantees, conformal set is impractical to compute exactly for many regression problems. We propose efficient algorithms to compute conformal prediction set using approximated solution of (convex) regularized empirical risk minimization. Our approaches rely on a new homotopy continuation technique for tracking the solution path with respect to sequential changes of the observations. We also provide a detailed analysis quantifying its complexity.

Thu Jan 16 2014
Machine Learning
Regression Conformal Prediction with Nearest Neighbours
Conformal Prediction (CP) produces regions that satisfy a given confidence level. The regions produced by any CP are automatically valid, however their tightness and usefulness depends on the nonconformity measure used by each CP.
0
0
0
Sat Jun 21 2014
Machine Learning
From conformal to probabilistic prediction
The method is applied to the standard USPS data set and gives encouraging results. It is based on conformal prediction.
0
0
0
Mon May 24 2021
Machine Learning
Optimized conformal classification using gradient descent approximation
Conformal predictors are an important class of algorithms that allow predictions to be made with a user-defined confidence level. Since accuracy is guaranteed, the performance of a conformal predictor is measured through the efficiency of the prediction sets.
2
0
0
Fri Feb 05 2021
Machine Learning
Exact Optimization of Conformal Predictors via Incremental and Decremental Learning
Conformal Predictors (CP) are wrappers around ML methods. High computational complexity limits their applicability to large datasets. We show that it is possible to speed up a CP classifier by studying it in conjunction with the underlying ML method.
0
0
0
Mon Mar 14 2016
Machine Learning
Criteria of efficiency for conformal prediction
We study optimal conformity measures for various criteria of efficiency of classification in an idealised setting. This leads to an important class of criteria that we call probabilistic. We consider unconditional and label-conditional conformal prediction.
0
0
0
Thu Jun 21 2007
Machine Learning
A tutorial on conformal prediction
Conformal prediction uses past experience to determine precise levels of confidence in new predictions. The most novel and valuable feature of conformal prediction is that if the successive predictions will be right of the time, even though they are based on an accumulating dataset rather than on independent datasets.
0
0
0