Neural Information Processing Systems http://nips.cc/

Forboundednonconvex losses and a batch sizem = 1, we additionally show that both generalization error and learning rate are independent ofd and K, and remain essentially the same asfortheSGD, evenfortwofunction evaluations.

This work was accomplished when Liyi Chen was an intern at Alibaba Cloud Computing.

B.1 BaselineGHN:GHN-1 GHNs were designed for NAS, which typically make strong assumptions about the choice of operations and their possible dimensions tomakesearch and learning feasible.

Consider the problem of training deep neural networks on large annotated datasets, such as ImageNet [1]. This problem can be formalized as finding optimal parameters for a given neural networka,parameterized byw,w.r.t.

Neural Information Processing Systems http://nips.cc/