On the Parallel I/O Optimality of Linear Algebra Kernels: Near-Optimal Matrix Factorizations.
Grzegorz KwasniewskiMarko KabicTal Ben-NunAlexandros Nikolaos ZiogasJens Eirik SaethreAndré GaillardTimo SchneiderMaciej BestaAnton KozhevnikovJoost VandeVondeleTorsten HoeflerPublished in: CoRR (2021)
Keyphrases
- linear algebra
- matrix factorization
- collaborative filtering
- missing data
- recommender systems
- low rank
- nonnegative matrix factorization
- negative matrix factorization
- tensor factorization
- kernel function
- singular value decomposition
- image processing
- computer architecture
- sparse matrices
- multiple kernel learning
- parallel computers
- feature space
- computer vision
- frequency domain
- data analysis
- multiscale