# Scaling Deep Networks with the Mesh Adaptive Direct Search algorithm

Source: [Scaling Deep Networks with the Mesh Adaptive Direct Search algorithm](<https://www.sota2.com/research/paper/68fa59f81e209131ce9bbc9d>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T16:13:41.541Z

Authors: Dounia Lakhmiri, Mahdi Zolnouri, Vahid Partovi Nia, Christophe Tribes, S\\'ebastien Le Digabel

Published: 2023-01-17T00:08:03.000Z

## Abstract

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 \\emph{reinforcement learning} and \\emph{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 \\emph{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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2301.06641>)

[PDF](<https://arxiv.org/pdf/2301.06641.pdf>)