Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in [1].
Exponentially convergent stochastic k-PCA without variance reduction
Authors: Cheng Tang
NeurIPS 2019 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | In this section, we present our empirical evaluation of Algorithm 1 to understand its convergence property on low-rank or effectively low-rank datasets 2. We first verified its performance on simulated low-rank data and effectively low-rank data, and then we evaluated its performance on two real-world effectively low-rank datasets. |
| Researcher Affiliation | Industry | Amazon AI New York, NY, 10001 EMAIL |
| Pseudocode | Yes | Algorithm 1 Matrix Krasulina |
| Open Source Code | Yes | Code will be available at https://github.com/chengtang48/neurips19. |
| Open Datasets | Yes | For MNIST [29], we use the 60000 training examples of digit pixel images, with d = 784. |
| Dataset Splits | No | The paper mentions using 60000 training examples for MNIST but does not explicitly detail any train/validation/test splits, specific percentages, or how validation was performed. |
| Hardware Specification | No | The paper does not provide specific details about the hardware used for running experiments (e.g., GPU/CPU models, memory specifications). |
| Software Dependencies | No | The paper does not provide specific version numbers for any software dependencies or libraries used in the experiments. |
| Experiment Setup | Yes | We initialized Algorithm 1 with a random matrix W o and ran it for one or a few epochs, each consists of 5000 iterations. We compare Algorithm 1 against the exponentially convergent VR-PCA: we initialize the algorithms with the same random matrix and we train (and repeated for 5 times) using the best constant learning rate we found empirically for each algorithm. |