The Convergence of Stochastic Gradient Descent in Asynchronous Shared Memory.
Dan AlistarhChristopher De SaNikola KonstantinovPublished in: CoRR (2018)
Keyphrases
- shared memory
- stochastic gradient descent
- step size
- convergence rate
- matrix factorization
- loss function
- least squares
- parallel algorithm
- message passing
- distributed memory
- convergence speed
- random forests
- online algorithms
- support vector machine
- shared memory multiprocessor
- regularization parameter
- recommender systems
- weight vector
- training set
- multiple kernel learning
- importance sampling
- multi view
- pairwise