English
Related papers

Related papers: Checkmate: Zero-Overhead Model Checkpointing via N…

200 papers

We present a novel, training-free approach to scene change detection. Our method leverages tracking models, which inherently perform change detection between consecutive frames of video by identifying common objects and detecting new or…

Computer Vision and Pattern Recognition · Computer Science 2025-01-22 Kyusik Cho , Dong Yeop Kim , Euntai Kim

The concept of conditional computation for deep nets has been proposed previously to improve model performance by selectively using only parts of the model conditioned on the sample it is processing. In this paper, we investigate…

Computer Vision and Pattern Recognition · Computer Science 2019-04-02 Zhourong Chen , Yang Li , Samy Bengio , Si Si

We investigate the training dynamics of two-layer neural networks when learning multi-index target functions. We focus on multi-pass gradient descent (GD) that reuses the batches multiple times and show that it significantly changes the…

Machine Learning · Statistics 2024-09-06 Yatin Dandi , Emanuele Troiani , Luca Arnaboldi , Luca Pesce , Lenka Zdeborová , Florent Krzakala

Time-dependent data-generating distributions have proven to be difficult for gradient-based training of neural networks, as the greedy updates result in catastrophic forgetting of previously learned knowledge. Despite the progress in the…

Machine Learning · Computer Science 2023-04-03 Matthias De Lange , Gido van de Ven , Tinne Tuytelaars

Under gang scheduling for large-scale distributed large language model (LLM) training, a single network anomaly can stall or abort an entire job. Current network fault tolerance mechanisms typically adopt a ``fallback and bypass'' approach…

Networking and Internet Architecture · Computer Science 2026-02-27 Shengkai Lin , Kairui Zhou , Hongtao Zhang , Yibo Wu , Yi Pan , Yihan Yang , Qinwei Yang , Wei Zhang , Arvind Krishnamurthy , Shizhen Zhao

Deep learning training relies on periodic checkpoints to recover from failures, but unsafe checkpoint installation can leave corrupted files on disk. This paper presents an experimental study of checkpoint installation protocols and…

Operating Systems · Computer Science 2025-11-25 Juha Jeon

Machine learning models are often learned by minimising a loss function on the training data using a gradient descent algorithm. These models often suffer from overfitting, leading to a decline in predictive performance on unseen data. A…

Owing to their remarkable learning capabilities and performance in real-world applications, the use of machine learning systems based on Neural Networks (NNs) has been continuously increasing. However, various case studies and empirical…

Machine Learning · Computer Science 2023-07-04 Mahum Naseer , Osman Hasan , Muhammad Shafique

Real-time network verification promises to automatically detect violations of network-wide reachability invariants on the data plane. To be useful in practice, these violations need to be detected in the order of milliseconds, without…

Networking and Internet Architecture · Computer Science 2017-03-02 Alex Horn , Ali Kheradmand , Mukul R. Prasad

We introduce a method called TracIn that computes the influence of a training example on a prediction made by the model. The idea is to trace how the loss on the test point changes during the training process whenever the training example…

Machine Learning · Computer Science 2020-11-17 Garima Pruthi , Frederick Liu , Mukund Sundararajan , Satyen Kale

Deep neural networks achieve state-of-the-art and sometimes super-human performance across various domains. However, when learning tasks sequentially, the networks easily forget the knowledge of previous tasks, known as "catastrophic…

Computer Vision and Pattern Recognition · Computer Science 2021-05-18 Shixiang Tang , Dapeng Chen , Jinguo Zhu , Shijie Yu , Wanli Ouyang

Supervised Continual learning involves updating a deep neural network (DNN) from an ever-growing stream of labeled data. While most work has focused on overcoming catastrophic forgetting, one of the major motivations behind continual…

Computer Vision and Pattern Recognition · Computer Science 2023-04-04 Md Yousuf Harun , Jhair Gallardo , Tyler L. Hayes , Christopher Kanan

In deep learning, Residual Networks (ResNets) have proven effective in addressing the vanishing gradient problem, allowing for the successful training of very deep networks. However, skip connections in ResNets can lead to gradient overlap,…

Machine Learning · Computer Science 2024-11-18 Juyoung Yun

This paper tackles the problem of making complex resource-constrained cyber-physical systems (CPS) resilient to sensor anomalies. In particular, we present a framework for checkpointing and roll-forward recovery of state-estimates in…

Systems and Control · Electrical Eng. & Systems 2023-01-02 Kaustubh Sridhar , Radoslav Ivanov , Vuk Lesi , Marcio Juliato , Manoj Sastry , Lily Yang , James Weimer , Oleg Sokolsky , Insup Lee

The success of deep learning comes at a tremendous computational and energy cost, and the scalability of training massively overparametrized neural networks is becoming a real barrier to the progress of artificial intelligence (AI). Despite…

Machine Learning · Computer Science 2024-02-09 Yichuan Deng , Hang Hu , Zhao Song , Omri Weinstein , Danyang Zhuo

In some studies \citep[e.g.,][]{zhang2016understanding} of deep learning, it is observed that over-parametrized deep neural networks achieve a small testing error even when the training error is almost zero. Despite numerous works towards…

Machine Learning · Statistics 2022-02-25 Yue Xing , Qifan Song , Guang Cheng

Continual learning aims to enable models to adapt to new datasets without losing performance on previously learned data, often assuming that prior data is no longer available. However, in many practical scenarios, both old and new data are…

Machine Learning · Computer Science 2025-03-03 Eli Verwimp , Guy Hacohen , Tinne Tuytelaars

We propose a novel deep neural network (DNN) based approximation architecture to learn estimates of measurements. We detail an algorithm that enables training of the DNN. The DNN estimator only uses measurements, if and when they are…

Machine Learning · Computer Science 2022-09-13 Shivangi Agarwal , Sanjit K. Kaul , Saket Anand , P. B. Sujit

Keypoint-based matching is a fundamental component of modern 3D vision systems, such as Structure-from-Motion (SfM) and SLAM. Most existing learning-based methods are trained on image pairs, a paradigm that fails to explicitly optimize for…

Computer Vision and Pattern Recognition · Computer Science 2026-05-18 Yepeng Liu , Hao Li , Liwen Yang , Fangzhen Li , Xudi Ge , Yuliang Gu , kuang Gao , Bing Wang , Guang Chen , Hangjun Ye , Yongchao Xu

Training a neural network using backpropagation algorithm requires passing error gradients sequentially through the network. The backward locking prevents us from updating network layers in parallel and fully leveraging the computing…

Machine Learning · Computer Science 2019-05-30 Zhouyuan Huo , Bin Gu , Heng Huang
‹ Prev 1 4 5 6 7 8 10 Next ›