Approximating the Top Eigenvector in Random Order Streams

Authors: Praneeth Kacham, David Woodruff

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

Reproducibility Variable Result LLM Response
Research Type Theoretical Our paper is purely theoretical studying space-efficient algorithms for approximating the top eigenvector. We prove all the claims made in the abstract and introduction.
Researcher Affiliation Collaboration Praneeth Kacham Google Research pkacham@google.com David P. Woodruff Carnegie Mellon University dwoodruf@cs.cmu.edu
Pseudocode Yes Algorithm 1: Approximate Eigenvector for Streams with no Large Norms
Open Source Code No The paper is purely theoretical and does not mention releasing any source code. The 'Experimental Result Reproducibility' section in the NeurIPS checklist is marked 'NA', indicating no experiments were conducted.
Open Datasets No The paper is purely theoretical and does not involve empirical experiments or datasets, thus no publicly available dataset is mentioned.
Dataset Splits No The paper is purely theoretical and does not involve empirical experiments or datasets, thus no dataset splits for validation are mentioned.
Hardware Specification No The paper is purely theoretical and does not conduct experiments, thus no hardware specifications are mentioned.
Software Dependencies No The paper is purely theoretical and does not conduct experiments, thus no specific software dependencies with version numbers are mentioned.
Experiment Setup No The paper is purely theoretical and does not conduct experiments, thus no experimental setup details like hyperparameters or training settings are provided.