Entropy-SGD: biasing gradient descent into wide valleys*This article is an updated version of Chaudhari P, Choromanska A, Soatto S, LeCun Y, Baldassi C, Borgs C, Chayes J, Sagun L, and Zecchina R 2017 Entropy-SGD: biasing gradient descent into wide valleys. Proc. of the International Conference of Learning and Representations (ICLR 2017).Code: https://github.com/ucla-vision/entropy-sgd. (20th December 2019)