Tensor Decomposition via Simultaneous Power Iteration

Authors: Po-An Wang, Chi-Jen Lu

ICML 2017 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical In this paper, we show how to find the eigenvectors simultaneously with the help of a new initialization procedure. This allows us to achieve a better running time in the batch setting, as well as a lower sample complexity in the streaming setting. Our algorithm is given in Algorithm 1, which consists of two phases: the initialization phase and the tensor power phase. Due to the space limitation, we will move all our proofs to the appendix in the supplementary material.
Researcher Affiliation Academia Po-An Wang 1 Chi-Jen Lu 1 1Academia Sinica, Taiwan.
Pseudocode Yes Algorithm 1 Robust tensor power method
Open Source Code No The paper is theoretical and does not provide any information about open-source code for the described methodology.
Open Datasets No The paper discusses theoretical models of data (e.g., 'noisy version of the tensor', 'stream of vectors') but does not specify a publicly available dataset used for empirical training or evaluation.
Dataset Splits No The paper is theoretical and does not describe any experimental dataset splits for training, validation, or testing.
Hardware Specification No The paper is theoretical and does not describe any specific hardware used for running experiments.
Software Dependencies No The paper is theoretical and does not mention specific software dependencies with version numbers for experimental replication.
Experiment Setup No The paper is theoretical and does not describe any experimental setup details, such as hyperparameters or training configurations.