English
Related papers

Related papers: Non-Determinism in TensorFlow ResNets

200 papers

Transfer learning is a widely-used paradigm in deep learning, where models pre-trained on standard datasets can be efficiently adapted to downstream tasks. Typically, better pre-trained models yield better transfer results, suggesting that…

Computer Vision and Pattern Recognition · Computer Science 2020-12-09 Hadi Salman , Andrew Ilyas , Logan Engstrom , Ashish Kapoor , Aleksander Madry

Graphics processing units (GPUs) are the de facto standard for processing deep learning (DL) tasks. Meanwhile, GPU failures, which are inevitable, cause severe consequences in DL tasks: they disrupt distributed trainings, crash inference…

Machine Learning · Computer Science 2022-01-31 Heting Liu , Zhichao Li , Cheng Tan , Rongqiu Yang , Guohong Cao , Zherui Liu , Chuanxiong Guo

Deep learning methods achieve state-of-the-art performance in many application scenarios. Yet, these methods require a significant amount of hyperparameters tuning in order to achieve the best results. In particular, tuning the learning…

Machine Learning · Computer Science 2017-11-07 Francesco Orabona , Tatiana Tommasi

Verifying computational processes in decentralized networks poses a fundamental challenge, particularly for Graphics Processing Unit (GPU) computations. Our investigation reveals significant limitations in existing approaches: exact…

Emerging Technologies · Computer Science 2025-01-10 Eric Boniardi , Stanley Bishop , Alison Haire

A range of approaches have been proposed for estimating the accuracy or robustness of the measured performance of IR methods. One is to use bootstrapping of test sets, which, as we confirm, provides an estimate of variation in performance.…

Information Retrieval · Computer Science 2025-09-26 Meng Yuan , Justin Zobel

Deep learning thrives with large neural networks and large datasets. However, larger networks and larger datasets result in longer training times that impede research and development progress. Distributed synchronous SGD offers a potential…

Computer Vision and Pattern Recognition · Computer Science 2018-05-02 Priya Goyal , Piotr Dollár , Ross Girshick , Pieter Noordhuis , Lukasz Wesolowski , Aapo Kyrola , Andrew Tulloch , Yangqing Jia , Kaiming He

Instability of trained models, i.e., the dependence of individual node predictions on random factors, can affect reproducibility, reliability, and trust in machine learning systems. In this paper, we systematically assess the prediction…

Machine Learning · Computer Science 2022-05-23 Max Klabunde , Florian Lemmerich

Training of large-scale deep neural networks is often constrained by the available computational resources. We study the effect of limited precision data representation and computation on neural network training. Within the context of…

Machine Learning · Computer Science 2015-02-11 Suyog Gupta , Ankur Agrawal , Kailash Gopalakrishnan , Pritish Narayanan

Despite the widespread empirical success of ResNet, the generalization properties of deep ResNet are rarely explored beyond the lazy training regime. In this work, we investigate \emph{scaled} ResNet in the limit of infinitely deep and wide…

Machine Learning · Computer Science 2024-03-18 Yihang Chen , Fanghui Liu , Yiping Lu , Grigorios G. Chrysos , Volkan Cevher

Deep neural networks (DNNs) achieve remarkable performance on a wide range of tasks, yet their mathematical analysis remains fragmented: stability and generalization are typically studied in disparate frameworks and on a case-by-case basis.…

Machine Learning · Statistics 2026-01-29 Jonathan Vacher

Very deep convolutional neural networks offer excellent recognition results, yet their computational expense limits their impact for many real-world applications. We introduce BlockDrop, an approach that learns to dynamically choose which…

Computer Vision and Pattern Recognition · Computer Science 2019-01-29 Zuxuan Wu , Tushar Nagarajan , Abhishek Kumar , Steven Rennie , Larry S. Davis , Kristen Grauman , Rogerio Feris

Regression neural networks (NNs) are most commonly trained by minimizing the mean squared prediction error, which is highly sensitive to outliers and data contamination. Existing robust training methods for regression NNs are often limited…

Machine Learning · Statistics 2026-02-10 Abhik Ghosh , Suryasis Jana

Deep neural networks have been shown to achieve state-of-the-art performance in several machine learning tasks. Stochastic Gradient Descent (SGD) is the preferred optimization algorithm for training these networks and asynchronous SGD…

Machine Learning · Computer Science 2016-04-06 Wei Zhang , Suyog Gupta , Xiangru Lian , Ji Liu

Uncertainty quantification in neural network promises to increase safety of AI systems, but it is not clear how performance might vary with the training set size. In this paper we evaluate seven uncertainty methods on Fashion MNIST and…

Machine Learning · Computer Science 2021-11-19 Matias Valdenegro-Toro

Modern deep generative models can now produce high-quality synthetic samples that are often indistinguishable from real training data. A growing body of research aims to understand why recent methods, such as diffusion and flow matching…

Machine Learning · Computer Science 2025-12-03 Quentin Bertrand , Anne Gagneux , Mathurin Massias , Rémi Emonet

In this article, we take one step toward understanding the learning behavior of deep residual networks, and supporting the observation that deep residual networks behave like ensembles. We propose a new convolutional neural network…

Computer Vision and Pattern Recognition · Computer Science 2024-10-30 Masoud Abdi , Saeid Nahavandi

Most existing Graph Neural Networks (GNNs) are proposed without considering the selection bias in data, i.e., the inconsistent distribution between the training set with test set. In reality, the test data is not even available during the…

Machine Learning · Computer Science 2022-01-27 Shaohua Fan , Xiao Wang , Chuan Shi , Kun Kuang , Nian Liu , Bai Wang

Because hyperspectral remote sensing images contain a lot of redundant information and the data structure is highly non-linear, leading to low classification accuracy of traditional machine learning methods. The latest research shows that…

Computer Vision and Pattern Recognition · Computer Science 2020-05-13 Xiangdong Zhang , Tengjun Wang , Yun Yang

The paper proposes an approach to training a convolutional neural network using information on the level of distortion of input data. The learning process is modified with an additional layer, which is subsequently deleted, so the…

Computer Vision and Pattern Recognition · Computer Science 2019-12-03 Igor Janiszewski , Dmitry Slugin , Vladimir V. Arlazarov

The past few years have witnessed a growth in size and computational requirements for training and inference with neural networks. Currently, a common approach to address these requirements is to use a heterogeneous distributed environment…