Distributed Black-Box Optimization via Error Correcting Codes

07/13/2019
by   Burak Bartan, et al.
0

We introduce a novel distributed derivative-free optimization framework that is resilient to stragglers. The proposed method employs coded search directions at which the objective function is evaluated, and a decoding step to find the next iterate. Our framework can be seen as an extension of evolution strategies and structured exploration methods where structured search directions were utilized. As an application, we consider black-box adversarial attacks on deep convolutional neural networks. Our numerical experiments demonstrate a significant improvement in the computation times.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset