Faster Principal Component Regression and Stable Matrix Chebyshev Approximation

Authors: Zeyuan Allen-Zhu, Yuanzhi Li

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

Reproducibility Variable Result LLM Response
Research Type Experimental We provide empirical evaluations in the full version of this paper.
Researcher Affiliation Collaboration 1Microsoft Reseaerch 2Princeton University. Correspondence to: Zeyuan Allen-Zhu <zeyuan@csail.mit.edu>, Yuanzhi Li <yuanzhil@cs.princeton.edu>.
Pseudocode Yes Since the high-level structure of our PCP algorithm is very clear, due to space limitation, we present the pseudocodes of our PCP and PCR algorithms in the full version.
Open Source Code No The paper states that a "Future version of this paper shall be found at https://arxiv.org/abs/1608.04773" and mentions that pseudocodes are in the "full version," but it does not provide an explicit statement or link to the open-source code for the methodology described in this paper.
Open Datasets No The paper mentions "a large-scale dataset" and references experiments in a "full version," but it does not provide concrete access information (link, DOI, repository name, or formal citation with authors/year) for any specific public dataset used.
Dataset Splits No The paper does not provide specific dataset split information (exact percentages, sample counts, citations to predefined splits, or detailed splitting methodology) for training, validation, or testing needed to reproduce the data partitioning.
Hardware Specification No The paper does not provide specific hardware details (exact GPU/CPU models, processor types with speeds, memory amounts, or detailed computer specifications) used for running its experiments.
Software Dependencies No The paper refers to various algorithms and methods like "SVRG (Johnson & Zhang, 2013)" and "Katyusha (Allen-Zhu, 2017)" but does not provide specific version numbers for these or any other software dependencies needed to replicate the experiment.
Experiment Setup No The paper states "We provide empirical evaluations in the full version of this paper," but it does not provide specific experimental setup details (concrete hyperparameter values, training configurations, or system-level settings) in the main text.