Optimal Multiclass U-Calibration Error and Beyond

Authors: Haipeng Luo, Spandan Senapati, Vatsal Sharan

NeurIPS 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical We resolve this question by showing that the optimal U-calibration error is Θ(KT) we start with a simple observation that the Follow-the-Perturbed Leader algorithm of Daskalakis and Syrgkanis (2016) achieves this upper bound, followed by a matching lower bound constructed with a specific proper loss
Researcher Affiliation Academia Haipeng Luo University of Southern California haipengl@usc.edu Spandan Senapati University of Southern California ssenapat@usc.edu Vatsal Sharan University of Southern California vsharan@usc.edu
Pseudocode Yes Algorithm 1 FTPL with geometric noise for U-calibration
Open Source Code No The paper does not include an unambiguous statement of code release or a link to a repository.
Open Datasets No The paper is theoretical and does not conduct experiments with datasets.
Dataset Splits No The paper is theoretical and does not conduct experiments with dataset splits.
Hardware Specification No The paper is theoretical and does not report hardware specifications for experiments.
Software Dependencies No The paper is theoretical and does not report software dependencies with version numbers for experiments.
Experiment Setup No The paper is theoretical and does not describe an experimental setup.