English
Related papers

Related papers: Delve into the Performance Degradation of Differen…

200 papers

In deep learning, it is common to use more network parameters than training points. In such scenarioof over-parameterization, there are usually multiple networks that achieve zero training error so that thetraining algorithm induces an…

Machine Learning · Computer Science 2023-08-22 Hung-Hsu Chou , Carsten Gieshoff , Johannes Maly , Holger Rauhut

This paper studies how neural network architecture affects the speed of training. We introduce a simple concept called gradient confusion to help formally analyze this. When gradient confusion is high, stochastic gradients produced by…

Machine Learning · Computer Science 2020-07-08 Karthik A. Sankararaman , Soham De , Zheng Xu , W. Ronny Huang , Tom Goldstein

Gradient-based learning algorithms have an implicit simplicity bias which in effect can limit the diversity of predictors being sampled by the learning procedure. This behavior can hinder the transferability of trained models by (i)…

Machine Learning · Computer Science 2022-11-24 Matteo Pagliardini , Martin Jaggi , François Fleuret , Sai Praneeth Karimireddy

In this work, we investigate a particular implicit bias in gradient descent training, which we term "Feature Averaging," and argue that it is one of the principal factors contributing to the non-robustness of deep neural networks. We show…

Machine Learning · Computer Science 2025-03-04 Binghui Li , Zhixuan Pan , Kaifeng Lyu , Jian Li

Learning rate is widely regarded as crucial for effective foundation model pretraining. Recent research explores and demonstrates the transferability of learning rate configurations across varying model and dataset sizes, etc. Nevertheless,…

Machine Learning · Computer Science 2025-12-23 Hongyuan Dong , Dingkang Yang , Xiao Liang , Chao Feng , Jiao Ran

In recent years, neural architecture search (NAS) has received intensive scientific and industrial interest due to its capability of finding a neural architecture with high accuracy for various artificial intelligence tasks such as image…

Machine Learning · Computer Science 2021-01-18 Martin Ferianc , Hongxiang Fan , Miguel Rodrigues

Accurate classification of medical images is essential for modern diagnostics. Deep learning advancements led clinicians to increasingly use sophisticated models to make faster and more accurate decisions, sometimes replacing human…

Computer Vision and Pattern Recognition · Computer Science 2024-05-07 Lunchen Xie , Eugenio Lomurno , Matteo Gambella , Danilo Ardagna , Manuel Roveri , Matteo Matteucci , Qingjiang Shi

One-shot neural architecture search (NAS) applies weight-sharing supernet to reduce the unaffordable computation overhead of automated architecture designing. However, the weight-sharing technique worsens the ranking consistency of…

Computer Vision and Pattern Recognition · Computer Science 2021-08-13 Ziwei Yang , Ruyi Zhang , Zhi Yang , Xubo Yang , Lei Wang , Zheyang Li

Neural networks are trained by choosing an architecture and training the parameters. The choice of architecture is often by trial and error or with Neural Architecture Search (NAS) methods. While NAS provides some automation, it often…

Machine Learning · Computer Science 2024-10-14 Zitong Huang , Mansooreh Montazerin , Ajitesh Srivastava

The accuracy of deep learning (e.g., convolutional neural networks) for an image classification task critically relies on the amount of labeled training data. Aiming to solve an image classification task on a new domain that lacks labeled…

Computer Vision and Pattern Recognition · Computer Science 2019-01-01 Xianghong Fang , Haoli Bai , Ziyi Guo , Bin Shen , Steven Hoi , Zenglin Xu

In this paper, we investigate a new variant of neural architecture search (NAS) paradigm -- searching with random labels (RLNAS). The task sounds counter-intuitive for most existing NAS algorithms since random label provides few information…

Computer Vision and Pattern Recognition · Computer Science 2021-05-26 Xuanyang Zhang , Pengfei Hou , Xiangyu Zhang , Jian Sun

Neural networks are powerful models that have a remarkable ability to extract patterns that are too complex to be noticed by humans or other machine learning models. Neural networks are the first class of models that can train end-to-end…

Machine Learning · Computer Science 2021-08-05 Ibrahim Alshubaily

Differentiable Architecture Search (DARTS) provides a baseline for searching effective network architectures based gradient, but it is accompanied by huge computational overhead in searching and training network architecture. Recently, many…

Machine Learning · Computer Science 2020-10-19 Zhaowen Wang , Wei Zhang , Zhiming Wang

Differentiable Neural Architecture Search (NAS) provides a promising avenue for automating the complex design of deep learning (DL) models. However, current differentiable NAS methods often face constraints in efficiency, operation…

Computer Vision and Pattern Recognition · Computer Science 2025-03-11 Lunchen Xie , Eugenio Lomurno , Matteo Gambella , Danilo Ardagna , Manual Roveri , Matteo Matteucci , Qingjiang Shi

While adversarial training and its variants have shown to be the most effective algorithms to defend against adversarial attacks, their extremely slow training process makes it hard to scale to large datasets like ImageNet. The key idea of…

Machine Learning · Computer Science 2022-06-07 Zhichao Huang , Yanbo Fan , Chen Liu , Weizhong Zhang , Yong Zhang , Mathieu Salzmann , Sabine Süsstrunk , Jue Wang

Neural architecture search (NAS) has shown promise towards automating neural network design for a given task, but it is computationally demanding due to training costs associated with evaluating a large number of architectures to find the…

Computer Vision and Pattern Recognition · Computer Science 2025-02-07 Shahid Siddiqui , Christos Kyrkou , Theocharis Theocharides

Motivated by the observation that humans can learn patterns from two given images at one time, we propose a dual pattern learning network architecture in this paper. Unlike conventional networks, the proposed architecture has two input…

Computer Vision and Pattern Recognition · Computer Science 2018-06-12 Haimin Zhang , Min Xu

Assisted by the availability of data and high performance computing, deep learning techniques have achieved breakthroughs and surpassed human performance empirically in difficult tasks, including object recognition, speech recognition, and…

Machine Learning · Computer Science 2019-01-23 Shaeke Salman , Xiuwen Liu

Several studies point out different causes of performance degradation in supervised machine learning. Problems such as class imbalance, overlapping, small-disjuncts, noisy labels, and sparseness limit accuracy in classification algorithms.…

Machine Learning · Computer Science 2020-04-17 Gustavo A. Valencia-Zapata , Carolina Gonzalez-Canas , Michael G. Zentner , Okan Ersoy , Gerhard Klimeck

This paper proposes a novel differentiable architecture search method by formulating it into a distribution learning problem. We treat the continuously relaxed architecture mixing weight as random variables, modeled by Dirichlet…

Machine Learning · Computer Science 2021-03-17 Xiangning Chen , Ruochen Wang , Minhao Cheng , Xiaocheng Tang , Cho-Jui Hsieh