Distribution-free binary classification: prediction sets, confidence intervals and calibration

Authors: Chirag Gupta, Aleksandr Podkopaev, Aaditya Ramdas

NeurIPS 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical We study three notions of uncertainty quantification calibration, confidence intervals and prediction sets for binary classification in the distribution-free setting, that is without making any distributional assumptions on the data. With a focus towards calibration, we establish a tripod of theorems that connect these three notions for score-based classifiers.
Researcher Affiliation Academia Chirag Gupta 1, Aleksandr Podkopaev 1,2, Aaditya Ramdas1,2 Machine Learning Department1 Department of Statistics and Data Science2 Carnegie Mellon University {chiragg,podkopaev,aramdas}@cmu.edu
Pseudocode No The paper does not contain structured pseudocode or algorithm blocks. Methods are described through textual explanations and mathematical formulations.
Open Source Code No The paper does not provide concrete access to source code (e.g., specific repository link, explicit code release statement, or code in supplementary materials) for the methodology described.
Open Datasets No The paper is theoretical and does not conduct experiments with specific datasets, therefore it does not provide access information for a publicly available or open dataset.
Dataset Splits No The paper is theoretical and does not report on experiments with specific datasets, therefore it does not provide specific dataset split information needed to reproduce data partitioning.
Hardware Specification No The paper is theoretical and does not report on specific experiments, therefore it does not provide specific hardware details used for running experiments.
Software Dependencies No The paper is theoretical and does not report on specific experiments, therefore it does not provide specific ancillary software details (e.g., library or solver names with version numbers).
Experiment Setup No The paper is theoretical and does not report on specific experiments, therefore it does not contain specific experimental setup details (e.g., concrete hyperparameter values, training configurations, or system-level settings).