Optimal Algorithms for Learning Partitions with Faulty Oracles

Authors: Adela DePavia, Olga Medrano Martin del Campo, Erasmo Tani

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

Reproducibility Variable Result LLM Response
Research Type Theoretical We design algorithms for this task and prove that they achieve optimal query complexity.
Researcher Affiliation Academia Adela Frances De Pavia University of Chicago adepavia@uchicago.edu Olga Medrano Martín del Campo University of Chicago omedranomdelc@uchicago.edu Erasmo Tani University of Chicago etani@uchicago.edu
Pseudocode Yes Algorithm 1: Learn(V, α, k, ℓyes)
Open Source Code No The paper is theoretical and does not mention providing open-source code for the described methodology.
Open Datasets No The paper is theoretical and does not involve experiments or datasets, thus no information about training data availability is provided.
Dataset Splits No The paper is theoretical and does not involve experiments or datasets, thus no information about validation splits is provided.
Hardware Specification No The paper is theoretical and does not involve empirical experiments, therefore no hardware specifications are mentioned.
Software Dependencies No The paper is theoretical and does not involve empirical experiments requiring specific software dependencies with version numbers.
Experiment Setup No The paper is theoretical and focuses on algorithm design and proofs rather than empirical experiments, so no experimental setup details are provided.