On the Equivalence between Online and Private Learnability beyond Binary Classification

Authors: Young Jung, Baekjin Kim, Ambuj Tewari

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

Reproducibility Variable Result LLM Response
Research Type Theoretical As this paper is purely theoretical, discussing broader impact is not applicable.
Researcher Affiliation Academia Young Hun Jung Department of Statistics University of Michigan Ann Arbor, MI 48109 yhjung@umich.edu Baekjin Kim Department of Statistics University of Michigan Ann Arbor, MI 48109 baekjin@umich.edu Ambuj Tewari Department of Statistics University of Michigan Ann Arbor, MI 48109 tewaria@umich.edu
Pseudocode Yes Algorithm 1 Standard optimal algorithm with tolerance τ (SOAτ) [...] Algorithm 2 COLORANDCHOOSE
Open Source Code No The paper does not provide concrete access to source code for the methodology described.
Open Datasets No This is a purely theoretical paper and does not involve the use of datasets for training or experimentation.
Dataset Splits No This is a purely theoretical paper and does not involve the use of datasets or their splits for validation.
Hardware Specification No This is a purely theoretical paper and does not report on experimental hardware specifications.
Software Dependencies No This is a purely theoretical paper and does not mention specific software dependencies with version numbers for experimental reproducibility.
Experiment Setup No This is a purely theoretical paper and does not describe an experimental setup with hyperparameters or training configurations.