AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

PAC Prediction Sets for Meta-Learning

Sangdon Park, Edgar Dobriban, Insup Lee, Osbert Bastani

NeurIPS 2022 · Label-efficient and robust learning › Recognition and long-tail · approach: Confidence calibration objectives · 1 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use Meta-PS (meta PAC prediction set) instead of naive pooled PSprototypical network score function · mini-ImageNet 5-way, epsilon 0.1PAC guarantee on prediction set errorImproved
use Meta-PS instead of PS-Test with 20 test-distribution shots per classprototypical network score function · mini-ImageNetprediction set sizeImproved
use Meta-PS instead of PAC variant of meta conformal predictionmini-ImageNet and FewRel · error over random test tasksprediction set error controlImproved
use Meta-PS instead of PS and Meta-CPprototypical network modified for imbalanced labels · CDC Heart Dataset, epsilon 0.1prediction set errorImproved
use Meta-PS instead of PS-Testprototypical network · CIFAR10-C 10-way, epsilon 0.2set size and labeling costImproved
set delta to 0.1 instead of 1e-5 (ablation)Meta-PS · mini-ImageNet per-calibration-set errorprediction set error per calibration setMixed

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy