Weighted Aggregating Stochastic Gradient Descent for Parallel Deep Learning.
Pengzhan GuoZeyang YeKeli XiaoWei ZhuPublished in: CoRR (2020)
Keyphrases
- deep learning
- stochastic gradient descent
- loss function
- matrix factorization
- unsupervised learning
- least squares
- step size
- machine learning
- mental models
- regularization parameter
- random forests
- online algorithms
- weakly supervised
- support vector machine
- object recognition
- learning algorithm
- natural images
- data sets
- weight vector