Natural evolution strategies converge on sphere functions

By Tom Schaul. 2012

21 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Optimization & Training

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Yoshua Bengio
2. Razvan Pascanu
3. Kyunghyun Cho
4. Sergey Levine
5. Mohit Bansal
6. Quoc V. Le
7. Ruslan Salakhutdinov
8. Jianfeng Gao

In Optimization & Training

1. Yoshua Bengio
2. Razvan Pascanu
3. Kyunghyun Cho
4. James Martens
5. Aaron C. Courville
6. Caglar Gulcehre
7. Frank Hutter
8. Li Deng

Citations in the corpus

• Revisiting Natural Gradient for Deep Networks (2013, methodology): “The approximations we use are meaningful only around θ , in Schaul (2012) it is shown that taking large steps might harm convergence.”