Abstract
Conformal Prediction (CP) is a powerful framework for constructing prediction sets with guaranteed coverage. However, recent studies have shown that integrating confidence calibration with CP can lead to a degradation in efficiency. In this paper, We propose an adaptive approach that considers the classifier’s uncertainty and employs entropy-based reweighting to enhance the efficiency of prediction sets for conformal classification. Our experimental results demonstrate that this method significantly improves efficiency. © 2024 R. Luo & N. Colombo.
| Original language | English |
|---|---|
| Title of host publication | The 13th Symposium on Conformal and Probabilistic Prediction with Applications, 9-11 September 2024, Politecnico di Milano, Milano, Italy |
| Publisher | ML Research Press |
| Pages | 264-276 |
| Publication status | Published - Sept 2024 |
| Event | 13th Symposium on Conformal and Probabilistic Prediction with Applications (COPA 2024) - Polytechnic University of Milan, Milan, Italy Duration: 9 Sept 2024 → 11 Sept 2024 https://proceedings.mlr.press/v230/ https://cml.rhul.ac.uk/copa2024/#nav-venue |
Publication series
| Name | Proceedings of Machine Learning Research |
|---|---|
| Volume | 230 |
| ISSN (Print) | 2640-3498 |
Conference
| Conference | 13th Symposium on Conformal and Probabilistic Prediction with Applications (COPA 2024) |
|---|---|
| Place | Italy |
| City | Milan |
| Period | 9/09/24 → 11/09/24 |
| Internet address |
Research Keywords
- confidence calibration
- Conformal prediction
- entropy reweighting
- neural networks
- temperature scaling
Fingerprint
Dive into the research topics of 'Entropy Reweighted Conformal Classification'. Together they form a unique fingerprint.Cite this
- APA
- Author
- BIBTEX
- Harvard
- Standard
- RIS
- Vancouver