English
Related papers

Related papers: Models Got Talent: Identifying High Performing Wea…

200 papers

Neural Architecture Search (NAS) can automatically design well-performed architectures of Deep Neural Networks (DNNs) for the tasks at hand. However, one bottleneck of NAS is the prohibitively computational cost largely due to the expensive…

Machine Learning · Computer Science 2021-07-29 Yuqiao Liu , Yehui Tang , Yanan Sun

To reduce the computational cost of convolutional neural networks (CNNs) on resource-constrained devices, structured pruning approaches have shown promise in lowering floating-point operations (FLOPs) without substantial drops in accuracy.…

Computer Vision and Pattern Recognition · Computer Science 2025-03-20 Lukas Meiner , Jens Mehnert , Alexandru Paul Condurache

The predictions of wide Bayesian neural networks are described by a Gaussian process, known as the Neural Network Gaussian Process (NNGP). Analytic forms for NNGP kernels are known for many models, but computing the exact kernel for…

Machine Learning · Computer Science 2020-11-13 Daniel S. Park , Jaehoon Lee , Daiyi Peng , Yuan Cao , Jascha Sohl-Dickstein

Neural Architecture Search (NAS) has become a de facto approach in the recent trend of AutoML to design deep neural networks (DNNs). Efficient or near-zero-cost NAS proxies are further proposed to address the demanding computational issues…

Machine Learning · Computer Science 2022-10-19 Yuhong Li , Jiajie Li , Cong Han , Pan Li , Jinjun Xiong , Deming Chen

One of the key steps in Neural Architecture Search (NAS) is to estimate the performance of candidate architectures. Existing methods either directly use the validation performance or learn a predictor to estimate the performance. However,…

Computer Vision and Pattern Recognition · Computer Science 2021-04-07 Yaofo Chen , Yong Guo , Qi Chen , Minli Li , Wei Zeng , Yaowei Wang , Mingkui Tan

The fundamental problem in Neural Architecture Search (NAS) is to efficiently find high-performing architectures from a given search space. We propose a simple but powerful method which we call FEAR, for ranking architectures in any search…

Machine Learning · Computer Science 2021-06-09 Debadeepta Dey , Shital Shah , Sebastien Bubeck

Understanding and modelling the performance of neural architectures is key to Neural Architecture Search (NAS). Performance predictors have seen widespread use in low-cost NAS and achieve high ranking correlations between predicted and…

Machine Learning · Computer Science 2023-04-19 Fred X. Han , Keith G. Mills , Fabian Chudak , Parsa Riahi , Mohammad Salameh , Jialin Zhang , Wei Lu , Shangling Jui , Di Niu

Optimization of radio hardware and AI-based network management software yield significant energy savings in radio access networks. The execution of underlying Machine Learning (ML) models, which enable energy savings through recommended…

Machine Learning · Computer Science 2025-04-04 Selim Ickin , Shruti Bothe , Aman Raparia , Nitin Khanna , Erik Sanders

Human Activity Recognition (HAR) using wearable and mobile sensors has gained momentum in last few years, in various fields, such as, healthcare, surveillance, education, entertainment. Nowadays, Edge Computing has emerged to reduce…

Signal Processing · Electrical Eng. & Systems 2019-10-01 Preeti Agarwal , Mansaf Alam

Most existing neural architecture search (NAS) algorithms are dedicated to and evaluated by the downstream tasks, e.g., image classification in computer vision. However, extensive experiments have shown that, prominent neural architectures,…

Machine Learning · Computer Science 2021-11-18 Yuhong Li , Cong Hao , Pan Li , Jinjun Xiong , Deming Chen

Many existing neural architecture search (NAS) solutions rely on downstream training for architecture evaluation, which takes enormous computations. Considering that these computations bring a large carbon footprint, this paper aims to…

Machine Learning · Computer Science 2021-11-29 Jingjing Xu , Liang Zhao , Junyang Lin , Rundong Gao , Xu Sun , Hongxia Yang

An effective and efficient architecture performance evaluation scheme is essential for the success of Neural Architecture Search (NAS). To save computational cost, most of existing NAS algorithms often train and evaluate intermediate neural…

Machine Learning · Computer Science 2021-09-27 Yixing Xu , Yunhe Wang , Kai Han , Yehui Tang , Shangling Jui , Chunjing Xu , Chang Xu

We propose a multitask pretraining approach ZeroPrompt for zero-shot generalization, focusing on task scaling and zero-shot prompting. While previous models are trained on only a few dozen tasks, we scale to 1,000 tasks for the first time…

Machine Learning · Computer Science 2022-11-01 Hanwei Xu , Yujun Chen , Yulun Du , Nan Shao , Yanggang Wang , Haiyu Li , Zhilin Yang

It is of great significance to estimate the performance of a given model architecture without training in the application of Neural Architecture Search (NAS) as it may take a lot of time to evaluate the performance of an architecture. In…

Machine Learning · Computer Science 2023-01-24 Kunlong Chen , Liu Yang , Yitian Chen , Kunjin Chen , Yidan Xu , Lujun Li

Many automated machine learning methods, such as those for hyperparameter and neural architecture optimization, are computationally expensive because they involve training many different model configurations. In this work, we present a new…

Machine Learning · Computer Science 2020-06-08 Martin Wistuba , Tejaswini Pedapati

Neural architecture search (NAS) has a great impact by automatically designing effective neural network architectures. However, the prohibitive computational demand of conventional NAS algorithms (e.g. $10^4$ GPU hours) makes it difficult…

Machine Learning · Computer Science 2019-02-26 Han Cai , Ligeng Zhu , Song Han

Neural architecture search has recently attracted lots of research efforts as it promises to automate the manual design of neural networks. However, it requires a large amount of computing resources and in order to alleviate this, a…

Machine Learning · Computer Science 2019-11-27 Alina Dubatovka , Efi Kokiopoulou , Luciano Sbaiz , Andrea Gesmundo , Gabor Bartok , Jesse Berent

Hollow-core fibers offer superior loss and latency characteristics compared to solid-core alternatives, yet the geometric complexity of nested antiresonance nodeless fibers (NANFs) makes traditional optimization computationally prohibitive.…

Machine Learning · Computer Science 2026-03-17 Rania A. Eltaieb , Sophie LaRochelle , Leslie A. Rusch

Neural architecture search (NAS) automates the design process of high-performing architectures, but remains bottlenecked by expensive performance evaluation. Most existing studies that achieve faster evaluation are mostly tied to cell-based…

Machine Learning · Computer Science 2025-10-07 Shiwen Qin , Alexander Auras , Shay B. Cohen , Elliot J. Crowley , Michael Moeller , Linus Ericsson , Jovita Lukasik

Neural Architecture Search (NAS) has been used recently to achieve improved performance in various tasks and most prominently in image classification. Yet, current search strategies rely on large labeled datasets, which limit their usage in…

Machine Learning · Computer Science 2020-07-06 Sapir Kaplan , Raja Giryes