The Convergence of Stochastic Gradient Descent in Asynchronous Shared Memory.
Dan AlistarhChristopher De SaNikola KonstantinovPublished in: PODC (2018)
Keyphrases
- shared memory
- stochastic gradient descent
- step size
- least squares
- message passing
- convergence rate
- parallel algorithm
- loss function
- matrix factorization
- convergence speed
- distributed memory
- random forests
- support vector machine
- multiple kernel learning
- importance sampling
- decision trees
- regularization parameter
- image processing
- distributed systems
- belief propagation
- image matching
- higher order
- weight vector
- objective function
- image sequences
- linear svm
- machine learning
- shared memory multiprocessor