Fast recovery from a union of subspaces

Authors: Chinmay Hegde, Piotr Indyk, Ludwig Schmidt

NeurIPS 2016 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We complement our theoretical results with experiments demonstrating that our framework also leads to improved time and sample complexity empirically.
Researcher Affiliation Academia Chinmay Hegde Iowa State University
Pseudocode Yes Algorithm 1 Approximate Subspace-IHT
Open Source Code No The paper does not provide any explicit statement or link to the source code for the methodology described.
Open Datasets No The paper uses “an image of the MIT logo” and “a symmetric matrix of size 2048 × 2048” but does not provide concrete access information (link, DOI, formal citation with authors/year) for these datasets or their public availability.
Dataset Splits No The paper does not explicitly provide specific dataset split information (percentages, sample counts, or detailed methodology) for training, validation, or testing.
Hardware Specification No The paper does not provide specific hardware details (exact GPU/CPU models, processor types, or memory amounts) used for running its experiments.
Software Dependencies No The paper mentions external tools like PROPACK [16] and block Krylov SVD [17] but does not provide specific ancillary software details (library or solver names with version numbers) used for its experiments.
Experiment Setup Yes SVP / IHT combined with a single iteration of a block Krylov SVD achieves the same phase transition as SVP with an exact SVD.