AI Paper Atlas

Research map / Learning theory and algorithms / Prediction and decision losses

PAC-Bayes Generalization Certificates for Learned Inductive Conformal Prediction

Apoorva Sharma, Sushant Veer, Asher Hancock, Heng Yang, Marco Pavone, Anirudha Majumdar

NeurIPS 2023 · Learning theory and algorithms › Prediction and decision losses · approach: Conformal prediction sets · 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 PAC-Bayes-constrained posterior optimization instead of split-based learned ICPLearned conformal prediction · 1-D regression, N = 500prediction-set efficiencyImproved
Use PAC-Bayes-constrained posterior optimization instead of split-based learned ICPLearned conformal prediction · Corrupted MNIST, N = 1000prediction set sizeImproved
Fine-tune the score function on corrupted calibration dataStandard ICP · Corrupted MNISTprediction set sizeImproved
Use PAC-Bayes optimization rather than learned ICP calibrated with Vovk 2aLearned ICP · Corrupted MNISTprediction set sizeMixed
Use PAC-Bayes optimization rather than learned ICP calibrated with Vovk 2bLearned ICP · Corrupted MNISTprediction set sizeHurt
Use PAC-Bayes optimization rather than split-based learned ICPLearned conformal prediction · Corrupted MNIST, varying data split ratioprediction set sizeImproved

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