On the Learnability of Multilabel Ranking

Authors: Vinod Raman, UNIQUE SUBEDI, Ambuj Tewari

NeurIPS 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical In this work, we characterize the learnability of multilabel ranking problems in both batch and online settings for a large family of ranking losses. Along the way, we give two equivalence classes of ranking losses based on learnability that capture most losses used in practice.
Researcher Affiliation Academia Vinod Raman Department of Statistics University of Michigan Ann Arbor, MI 48104 vkraman@umich.edu Unique Subedi Department of Statistics University of Michigan Ann Arbor, MI 48104 subedi@umich.edu Ambuj Tewari Department of Statistics University of Michigan Ann Arbor, MI 48104 tewaria@umich.edu
Pseudocode Yes Algorithm 2 Expert (b, φ); Algorithm 3 Agnostic Online Learner Q for H w.r.t.
Open Source Code No The paper does not provide any explicit statements about releasing source code, nor does it include links to a code repository.
Open Datasets No The paper is theoretical and does not describe experiments that use datasets, nor does it provide information about the public availability of any dataset.
Dataset Splits No The paper is theoretical and does not involve empirical validation on datasets, thus no details on training/test/validation splits are provided.
Hardware Specification No The paper is theoretical and does not describe empirical experiments, therefore no hardware specifications are mentioned.
Software Dependencies No The paper focuses on theoretical characterization and does not provide specific software dependencies or version numbers.
Experiment Setup No The paper is theoretical and does not include details about an experimental setup, hyperparameters, or training configurations.