Invited Talk
in
Workshop: Negative Dependence: Theory and Applications in Machine Learning
Cheng Zhang: Active Mini-Batch Sampling using Repulsive Point Processes
Cheng Zhang
Abstract:
We explore active mini-batch selection using repulsive point processes for stochastic gradient descent (SGD). Our approach simultaneously introduces active bias and leads to stochastic gradients with lower variance. We show theoretically and empirically that our approach improves over standard SGD both in terms of convergence speed as well as final model performance.
Chat is not available.