Binary Classification with Karmic, Threshold-Quasi-Concave Metrics

Authors: Bowei Yan, Sanmi Koyejo, Kai Zhong, Pradeep Ravikumar

ICML 2018 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical In this paper, we advance this understanding of binary classification for complex performance measures by identifying two key properties: a so-called Karmic property, and a more technical threshold-quasiconcavity property, which we show is milder than existing structural assumptions imposed on performance measures. Under these properties, we show that the Bayes optimal classifier is a threshold function of the conditional probability of positive class. We then leverage this result to come up with a computationally practical plug-in classifier, via a novel threshold estimator, and further, provide a novel statistical analysis of classification error with respect to complex performance measures.
Researcher Affiliation Academia 1University of Texas at Austin, Austin, Texas, USA 2University of Illinois at Urbana-Champaign, Champaign, Illinois, USA 3Carnegie Mellon University, Pittsburgh, Pennsylvania, USA.
Pseudocode Yes Algorithm 1 Two-step Plug-in Classifier for General Metrics
Open Source Code No The paper does not provide concrete access to source code for the methodology described, nor does it state that code is available.
Open Datasets No The paper does not provide concrete access information for a publicly available or open dataset. It refers to theoretical models such as the 'Gaussian generative model' and 'β-H older densities' for analytical purposes rather than specific datasets for experimentation.
Dataset Splits No The paper does not provide specific dataset split information as it focuses on theoretical analysis and does not report on empirical experiments with datasets.
Hardware Specification No The paper does not provide specific hardware details used for running experiments, as the research presented is theoretical and does not report on empirical experiments.
Software Dependencies No The paper does not provide specific ancillary software details (e.g., library or solver names with version numbers), as the research presented is theoretical and does not report on empirical experiments.
Experiment Setup No The paper does not contain specific experimental setup details (e.g., hyperparameters, training configurations), as the research presented is theoretical and does not report on empirical experiments.