Scaling Deep Networks with the Mesh Adaptive Direct Search algorithm

01/17/2023
by   Dounia Lakhmiri, et al.
0

Deep neural networks are getting larger. Their implementation on edge and IoT devices becomes more challenging and moved the community to design lighter versions with similar performance. Standard automatic design tools such as reinforcement learning and evolutionary computing fundamentally rely on cheap evaluations of an objective function. In the neural network design context, this objective is the accuracy after training, which is expensive and time-consuming to evaluate. We automate the design of a light deep neural network for image classification using the Mesh Adaptive Direct Search(MADS) algorithm, a mature derivative-free optimization method that effectively accounts for the expensive blackbox nature of the objective function to explore the design space, even in the presence of constraints.Our tests show competitive compression rates with reduced numbers of trials.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset