Dynamical mean-field theory for stochastic gradient descent in Gaussian mixture classification

Francesca Mignacco, Florent Krzakala, Pierfrancesco Urbani, Lenka Zdeborová. Dynamical mean-field theory for stochastic gradient descent in Gaussian mixture classification. In Hugo Larochelle, Marc'Aurelio Ranzato, Raia Hadsell, Maria-Florina Balcan, Hsuan-Tien Lin, editors, Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6-12, 2020, virtual. 2020. [doi]

Authors

Francesca Mignacco

This author has not been identified. Look up 'Francesca Mignacco' in Google

Florent Krzakala

This author has not been identified. Look up 'Florent Krzakala' in Google

Pierfrancesco Urbani

This author has not been identified. Look up 'Pierfrancesco Urbani' in Google

Lenka Zdeborová

This author has not been identified. Look up 'Lenka Zdeborová' in Google