GASGD: stochastic gradient descent for distributed asynchronous matrix completion via graph partitioning.
Fabio PetroniLeonardo QuerzoniPublished in: RecSys (2014)
Keyphrases
- graph partitioning
- stochastic gradient descent
- matrix factorization
- least squares
- step size
- graph model
- image segmentation
- random forests
- loss function
- weighted graph
- clustering algorithm
- online algorithms
- low rank
- spectral clustering
- data clustering
- weight vector
- collaborative filtering
- regularization parameter
- support vector machine
- support vector
- computer vision
- adjacency matrix