Learning to Learn without Gradient Descent by Gradient Descent
ICML, pp. 748-756, 2017.
We learn recurrent neural network optimizers trained on simple synthetic functions by gradient descent. We show that these learned optimizers exhibit a remarkable degree of transfer in that they can be used to efficiently optimize a broad range of derivative-free black-box functions, including Gaussian process bandits, simple control obje...More
PPT (Upload PPT)