English
Related papers

Related papers: Scaling Deep Networks with the Mesh Adaptive Direc…

200 papers

Deep neural networks achieve remarkable performance in many computer vision tasks. Most state-of-the-art (SOTA) semantic segmentation and object detection approaches reuse neural network architectures designed for image classification as…

Computer Vision and Pattern Recognition · Computer Science 2020-04-10 Jiemin Fang , Yuzhu Sun , Kangjian Peng , Qian Zhang , Yuan Li , Wenyu Liu , Xinggang Wang

Deep learning has revolutionized computer vision, but it achieved its tremendous success using deep network architectures which are mostly hand-crafted and therefore likely suboptimal. Neural Architecture Search (NAS) aims to bridge this…

Computer Vision and Pattern Recognition · Computer Science 2025-02-10 Ondřej Týbl , Lukáš Neumann

Computational models in fields such as computational neuroscience are often evaluated via stochastic simulation or numerical approximation. Fitting these models implies a difficult optimization problem over complex, possibly noisy parameter…

Machine Learning · Statistics 2017-11-03 Luigi Acerbi , Wei Ji Ma

Neural networks have been notorious for being computationally expensive. This is mainly because neural networks are often over-parametrized and most likely have redundant nodes or layers as they are getting deeper and wider. Their demand…

Computer Vision and Pattern Recognition · Computer Science 2019-10-08 Georgios Tzelepis , Ahraz Asif , Saimir Baci , Selcuk Cavdar , Eren Erdal Aksoy

Over the past few years, as large language models have ushered in an era of intelligence emergence, there has been an intensified focus on scaling networks. Currently, many network architectures are designed manually, often resulting in…

Computer Vision and Pattern Recognition · Computer Science 2024-05-14 Kai Liu , Ruohui Wang , Jianfei Gao , Kai Chen

Efficient deep learning computing requires algorithm and hardware co-design to enable specialization: we usually need to change the algorithm to reduce memory footprint and improve energy efficiency. However, the extra degree of freedom…

Machine Learning · Computer Science 2019-04-25 Song Han , Han Cai , Ligeng Zhu , Ji Lin , Kuan Wang , Zhijian Liu , Yujun Lin

This work introduces StoMADS, a stochastic variant of the mesh adaptive direct-search (MADS) algorithm originally developed for deterministic blackbox optimization. StoMADS considers the unconstrained optimization of an objective function f…

Optimization and Control · Mathematics 2019-11-05 Charles Audet , Kwassi Joseph Dzahini , Michael Kokkolaras , Sébastien Le Digabel

Neural Architecture Search (NAS) aims to automatically find effective architectures within a predefined search space. However, the search space is often extremely large. As a result, directly searching in such a large search space is…

Computer Vision and Pattern Recognition · Computer Science 2024-06-07 Yaofo Chen , Yong Guo , Daihai Liao , Fanbing Lv , Hengjie Song , James Tin-Yau Kwok , Mingkui Tan

Neural Architecture Search (NAS) is a collection of methods to craft the way neural networks are built. We apply this idea to Federated Learning (FL), wherein predefined neural network models are trained on the client/device data. This…

Machine Learning · Computer Science 2020-10-21 Anubhav Garg , Amit Kumar Saha , Debo Dutta

Deep neural networks achieve remarkable performance in many computer vision tasks. Most state-of-the-art (SOTA) semantic segmentation and object detection approaches reuse neural network architectures designed for image classification as…

Computer Vision and Pattern Recognition · Computer Science 2020-12-17 Jiemin Fang , Yuzhu Sun , Qian Zhang , Kangjian Peng , Yuan Li , Wenyu Liu , Xinggang Wang

Neural architecture search (NAS) has been an active direction of automatic machine learning (Auto-ML), aiming to explore efficient network structures. The searched architecture is evaluated by training on datasets with fixed data…

Machine Learning · Computer Science 2022-01-31 Xiaoxing Wang , Xiangxiang Chu , Junchi Yan , Xiaokang Yang

The design of compact deep neural networks is a crucial task to enable widespread adoption of deep neural networks in the real-world, particularly for edge and mobile scenarios. Due to the time-consuming and challenging nature of manually…

Neural and Evolutionary Computing · Computer Science 2019-10-16 Mohammad Javad Shafiee , Andrew Hryniowski , Francis Li , Zhong Qiu Lin , Alexander Wong

In this paper, we propose an algorithmic framework to automatically generate efficient deep neural networks and optimize their associated hyperparameters. The framework is based on evolving directed acyclic graphs (DAGs), defining a more…

Neural and Evolutionary Computing · Computer Science 2024-05-15 Julie Keisler , El-Ghazali Talbi , Sandra Claudel , Gilles Cabriel

The work presented here is motivated by the development of StoDARS, a framework for large-scale stochastic blackbox optimization that not only is both an algorithmic and theoretical extension of the stochastic directional direct-search…

Optimization and Control · Mathematics 2024-03-21 K. J. Dzahini , S. M. Wild

Deep learning has become in recent years a cornerstone tool fueling key innovations in the industry, such as autonomous driving. To attain good performances, the neural network architecture used for a given application must be chosen with…

Computer Vision and Pattern Recognition · Computer Science 2021-09-17 Anthony Cazasnoves , Pierre-Antoine Ganaye , Kévin Sanchis , Tugdual Ceillier

Neural architecture search (NAS) has gained significant traction in automating the design of neural networks. To reduce search time, differentiable architecture search (DAS) reframes the traditional paradigm of discrete candidate sampling…

Machine Learning · Computer Science 2025-11-26 Xiaoyun Liu , Divya Saxena , Jiannong Cao , Yuqing Zhao , Penghui Ruan

In deep learning, performance is strongly affected by the choice of architecture and hyperparameters. While there has been extensive work on automatic hyperparameter optimization for simple spaces, complex spaces such as the space of deep…

Machine Learning · Statistics 2017-05-01 Renato Negrinho , Geoff Gordon

We introduce a novel approach to automatic unstructured mesh generation using machine learning to predict an optimal finite element mesh for a previously unseen problem. The framework that we have developed is based around training an…

Numerical Analysis · Mathematics 2020-04-16 Zheyan Zhang , Yongxing Wang , Peter K. Jimack , He Wang

Designing effective neural networks is fundamentally important in deep multimodal learning. Most existing works focus on a single task and design neural architectures manually, which are highly task-specific and hard to generalize to…

Computer Vision and Pattern Recognition · Computer Science 2020-10-13 Zhou Yu , Yuhao Cui , Jun Yu , Meng Wang , Dacheng Tao , Qi Tian

The escalating parameter counts in modern deep learning models pose a fundamental challenge to efficient training and resolution of overfitting. We address this by introducing the \emph{Mapping Networks} which replace the high dimensional…

Computer Vision and Pattern Recognition · Computer Science 2026-02-24 Lord Sen , Shyamapada Mukherjee