Summary of Provably Robust Conformal Prediction with Improved Efficiency, by Ge Yan et al.
Provably Robust Conformal Prediction with Improved Efficiency
by Ge Yan, Yaniv Romano, Tsui-Wei Weng
First submitted to arxiv on: 30 Apr 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The proposed paper addresses the limitations of Randomized Smoothed Conformal Prediction (RSCP) by introducing a novel framework called RSCP+, which provides provable robustness guarantees in evaluation. The authors also propose two methods, Post-Training Transformation (PTT) and Robust Conformal Training (RCT), to reduce prediction set size with minimal computation overhead. These methods are evaluated on CIFAR10, CIFAR100, and ImageNet datasets, showing significant improvements in efficiency and robustness. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper fixes the flaws of RSCP by introducing a new framework called RSCP+ that provides robustness guarantees in evaluation. The authors also introduce two new methods to reduce prediction set size with little computation overhead. These methods are tested on different datasets like CIFAR10, CIFAR100, and ImageNet, showing great results. |
