Stochastic gradient descent performs variational inference, converges to limit cycles for deep networks

Pratik Chaudhari, Stefano Soatto. Stochastic gradient descent performs variational inference, converges to limit cycles for deep networks. In 6th International Conference on Learning Representations, ICLR 2018, Vancouver, BC, Canada, April 30 - May 3, 2018, Conference Track Proceedings. OpenReview.net, 2018. [doi]

Authors

Pratik Chaudhari

This author has not been identified. Look up 'Pratik Chaudhari' in Google

Stefano Soatto

This author has not been identified. Look up 'Stefano Soatto' in Google