English
Related papers

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

200 papers

Checkpointing enables the training of deep learning models under restricted memory budgets by freeing intermediate activations from memory and recomputing them on demand. Current checkpointing techniques statically plan these recomputations…

Machine Learning · Computer Science 2021-03-19 Marisa Kirisame , Steven Lyubomirsky , Altan Haan , Jennifer Brennan , Mike He , Jared Roesch , Tianqi Chen , Zachary Tatlock

As the state-of-the-art machine learning methods in many fields rely on larger datasets, storing datasets and training models on them become significantly more expensive. This paper proposes a training set synthesis technique for…

Computer Vision and Pattern Recognition · Computer Science 2021-03-09 Bo Zhao , Konda Reddy Mopuri , Hakan Bilen

An iterative method of learning has become a paradigm for training deep convolutional neural networks (DCNN). However, utilizing a non-iterative learning strategy can accelerate the training process of the DCNN and surprisingly such…

Machine Learning · Computer Science 2018-09-18 Yimin Yang , Q. M. Jonathan Wu , Xiexing Feng , Thangarajah Akilan

Dropout is a simple but efficient regularization technique for achieving better generalization of deep neural networks (DNNs); hence it is widely used in tasks based on DNNs. During training, dropout randomly discards a portion of the…

Neural and Evolutionary Computing · Computer Science 2020-10-22 Hiroshi Inoue

Deep neural networks (DNNs) have become ubiquitous thanks to their remarkable ability to model complex patterns across various domains such as computer vision, speech recognition, robotics, etc. While large DNN models are often more…

Machine Learning · Computer Science 2025-11-18 Omkar Shende , Gayathri Ananthanarayanan , Marcello Traiola

Most stochastic gradient descent algorithms can optimize neural networks that are sub-differentiable in their parameters; however, this implies that the neural network's activation function must exhibit a degree of continuity which limits…

Neural and Evolutionary Computing · Computer Science 2021-12-16 Anastasis Kratsios , Behnoosh Zamanlooy

Training a neural network for a classification task typically assumes that the data to train are given from the beginning. However, in the real world, additional data accumulate gradually and the model requires additional training without…

Machine Learning · Computer Science 2020-04-22 Jangho Kim , Jeesoo Kim , Nojun Kwak

With the growing importance of large network models and enormous training datasets, GPUs have become increasingly necessary to train neural networks. This is largely because conventional optimization algorithms rely on stochastic gradient…

Machine Learning · Computer Science 2016-05-09 Gavin Taylor , Ryan Burmeister , Zheng Xu , Bharat Singh , Ankit Patel , Tom Goldstein

Dynamic DNN optimization techniques such as layer-skipping offer increased adaptability and efficiency gains but can lead to i) a larger memory footprint as in decision gates, ii) increased training complexity (e.g., with non-differentiable…

Machine Learning · Computer Science 2025-05-26 Guilherme Korol , Antonio Carlos Schneider Beck , Jeronimo Castrillon

Efficient construction of checkpoints/snapshots is a critical tool for training and diagnosing deep learning models. In this paper, we propose a lossy compression scheme for checkpoint constructions (called LC-Checkpoint). LC-Checkpoint…

Machine Learning · Computer Science 2020-09-29 Yu Chen , Zhenming Liu , Bin Ren , Xin Jin

Fault-aware retraining has emerged as a prominent technique for mitigating permanent faults in Deep Neural Network (DNN) hardware accelerators. However, retraining leads to huge overheads, specifically when used for fine-tuning large DNNs…

Hardware Architecture · Computer Science 2023-05-23 Muhammad Abdullah Hanif , Muhammad Shafique

Coordinated checkpointing is an effective fault tolerant technique in distributed system as it avoids the domino effect and require minimum storage requirement. Most of the earlier coordinated checkpoint algorithms block their computation…

Distributed, Parallel, and Cluster Computing · Computer Science 2010-07-15 Surender Kumar , R. K. Chauhan , Parveen Kumar

Models pre-trained on large-scale datasets are often fine-tuned to support newer tasks and datasets that arrive over time. This process necessitates storing copies of the model over time for each task that the pre-trained model is…

Computer Vision and Pattern Recognition · Computer Science 2023-09-22 Chaitanya Devaguptapu , Samarth Sinha , K J Joseph , Vineeth N Balasubramanian , Animesh Garg

We present a novel and flexible architecture for point cloud segmentation with dual-representation iterative learning. In point cloud processing, different representations have their own pros and cons. Thus, finding suitable ways to…

Computer Vision and Pattern Recognition · Computer Science 2021-08-10 Maosheng Ye , Shuangjie Xu , Tongyi Cao , Qifeng Chen

Neural networks have enabled state-of-the-art approaches to achieve incredible results on computer vision tasks such as object detection. However, such success greatly relies on costly computation resources, which hinders people with cheap…

Computer Vision and Pattern Recognition · Computer Science 2019-11-28 Chien-Yao Wang , Hong-Yuan Mark Liao , I-Hau Yeh , Yueh-Hua Wu , Ping-Yang Chen , Jun-Wei Hsieh

Recurrent neural networks are a successful neural architecture for many time-dependent problems, including time series analysis, forecasting, and modeling of dynamical systems. Training such networks with backpropagation through time is a…

Machine Learning · Computer Science 2025-01-30 Erik Lien Bolager , Ana Cukarska , Iryna Burak , Zahra Monfared , Felix Dietrich

Recurrent neural networks (RNNs) have recently demonstrated strong performance and faster inference than Transformers at comparable parameter budgets. However, the recursive gradient computation with the backpropagation through time (or…

Machine Learning · Computer Science 2025-04-01 Paul Caillon , Erwan Fagnou , Alexandre Allauzen

Deep Neural Network (DNN) models are usually trained sequentially from one layer to another, which causes forward, backward and update locking's problems, leading to poor performance in terms of training time. The existing parallel…

Distributed, Parallel, and Cluster Computing · Computer Science 2022-07-25 Samson B. Akintoye , Liangxiu Han , Huw Lloyd , Xin Zhang , Darren Dancey , Haoming Chen , Daoqiang Zhang

A distributed system consisting of a huge number of computational entities is prone to faults, because faults in a few nodes cause the entire system to fail. Consequently, fault tolerance of distributed systems is a critical issue.…

Distributed, Parallel, and Cluster Computing · Computer Science 2021-03-30 Junya Nakamura , Yonghwan Kim , Yoshiaki Katayama , Toshimitsu Masuzawa

The goal of continual learning (CL) is to efficiently update a machine learning model with new data without forgetting previously-learned knowledge. Most widely-used CL methods rely on a rehearsal memory of data points to be reused while…

Machine Learning · Computer Science 2022-03-29 Lukas Balles , Giovanni Zappella , Cédric Archambeau