Streaming Principal Component Analysis in Noisy Setting

Authors: Teodor Vanislavov Marinov, Poorya Mianjy, Raman Arora

ICML 2018 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental 7. Experimental Results
Researcher Affiliation Academia 1Department of Computer Science, Johns Hopkins University, Baltimore, USA.
Pseudocode No The paper refers to 'Algorithm 2 of (Warmuth & Kuzmin, 2008)' but does not include its own pseudocode or clearly labeled algorithm block.
Open Source Code No The paper does not contain any explicit statements about releasing source code or provide links to a code repository.
Open Datasets Yes We evaluate empirical performance of our algorithms with missing data (MGDMD, Oja-MD) and partial observations (MGD-PO, Oja PO) on two real datasets, MNIST (Le Cun et al., 1998) and XRMB (Westbury, 1994)...
Dataset Splits Yes The initial learning rate η0 is chosen using cross validation on a held-out set.
Hardware Specification No The paper discusses computational complexity and runtime, but does not provide specific details on the hardware (e.g., GPU models, CPU types, or memory) used for running the experiments.
Software Dependencies No The paper discusses various algorithms and methods (e.g., MGD, Oja's algorithm) but does not list specific software dependencies with their version numbers required to replicate the experiments.
Experiment Setup Yes The learning rate for variants of MGD and Oja s algorithm is set to ηt = η0/t, for MGD-PO to ηt = r2η0/t, and for MGDMD to ηt = q2 η0/t. The initial learning rate η0 is chosen using cross validation on a held-out set.