Multi-Modal Conformal Prediction Regions with Simple Structures by Optimizing Convex Shape Templates
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915182505099264 |
|---|---|
| author | Tumu, Renukanandan Cleaveland, Matthew Mangharam, Rahul Pappas, George J. Lindemann, Lars |
| author_facet | Tumu, Renukanandan Cleaveland, Matthew Mangharam, Rahul Pappas, George J. Lindemann, Lars |
| contents | Conformal prediction is a statistical tool for producing prediction regions for machine learning models that are valid with high probability. A key component of conformal prediction algorithms is a \emph{non-conformity score function} that quantifies how different a model's prediction is from the unknown ground truth value. Essentially, these functions determine the shape and the size of the conformal prediction regions. While prior work has gone into creating score functions that produce multi-model prediction regions, such regions are generally too complex for use in downstream planning and control problems. We propose a method that optimizes parameterized \emph{shape template functions} over calibration data, which results in non-conformity score functions that produce prediction regions with minimum volume. Our approach results in prediction regions that are \emph{multi-modal}, so they can properly capture residuals of distributions that have multiple modes, and \emph{practical}, so each region is convex and can be easily incorporated into downstream tasks, such as a motion planner using conformal prediction regions. Our method applies to general supervised learning tasks, while we illustrate its use in time-series prediction. We provide a toolbox and present illustrative case studies of F16 fighter jets and autonomous vehicles, showing an up to $68\%$ reduction in prediction region area compared to a circular baseline region. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2312_07434 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Multi-Modal Conformal Prediction Regions with Simple Structures by Optimizing Convex Shape Templates Tumu, Renukanandan Cleaveland, Matthew Mangharam, Rahul Pappas, George J. Lindemann, Lars Machine Learning Systems and Control Conformal prediction is a statistical tool for producing prediction regions for machine learning models that are valid with high probability. A key component of conformal prediction algorithms is a \emph{non-conformity score function} that quantifies how different a model's prediction is from the unknown ground truth value. Essentially, these functions determine the shape and the size of the conformal prediction regions. While prior work has gone into creating score functions that produce multi-model prediction regions, such regions are generally too complex for use in downstream planning and control problems. We propose a method that optimizes parameterized \emph{shape template functions} over calibration data, which results in non-conformity score functions that produce prediction regions with minimum volume. Our approach results in prediction regions that are \emph{multi-modal}, so they can properly capture residuals of distributions that have multiple modes, and \emph{practical}, so each region is convex and can be easily incorporated into downstream tasks, such as a motion planner using conformal prediction regions. Our method applies to general supervised learning tasks, while we illustrate its use in time-series prediction. We provide a toolbox and present illustrative case studies of F16 fighter jets and autonomous vehicles, showing an up to $68\%$ reduction in prediction region area compared to a circular baseline region. |
| title | Multi-Modal Conformal Prediction Regions with Simple Structures by Optimizing Convex Shape Templates |
| topic | Machine Learning Systems and Control |
| url | https://arxiv.org/abs/2312.07434 |