English
Related papers

Related papers: Accelerated Training via Incrementally Growing Neu…

200 papers

Adaptive learning is an area of educational technology that consists in delivering personalized learning experiences to address the unique needs of each learner. An important subfield of adaptive learning is learning path personalization:…

Machine Learning · Computer Science 2023-05-12 Jean Vassoyan , Jill-Jênn Vie , Pirmin Lemberger

Recent work has shown that it is possible to train deep neural networks that are provably robust to norm-bounded adversarial perturbations. Most of these methods are based on minimizing an upper bound on the worst-case loss over all…

We build a theoretical framework for designing and understanding practical meta-learning methods that integrates sophisticated formalizations of task-similarity with the extensive literature on online convex optimization and sequential…

Machine Learning · Computer Science 2019-12-10 Mikhail Khodak , Maria-Florina Balcan , Ameet Talwalkar

This paper tackles the problem of training a deep convolutional neural network of both low-bitwidth weights and activations. Optimizing a low-precision network is very challenging due to the non-differentiability of the quantizer, which may…

Computer Vision and Pattern Recognition · Computer Science 2021-06-07 Bohan Zhuang , Jing Liu , Mingkui Tan , Lingqiao Liu , Ian Reid , Chunhua Shen

Recently many first and second order variants of SGD have been proposed to facilitate training of Deep Neural Networks (DNNs). A common limitation of these works stem from the fact that they use the same learning rate across all instances…

Machine Learning · Computer Science 2021-05-31 Shreyas Saxena , Nidhi Vyas , Dennis DeCoste

In scalable machine learning systems, model training is often parallelized over multiple nodes that run without tight synchronization. Most analysis results for the related asynchronous algorithms use an upper bound on the information…

Machine Learning · Computer Science 2022-04-12 Xuyang Wu , Sindri Magnusson , Hamid Reza Feyzmahdavian , Mikael Johansson

The most straightforward method to accelerate Stochastic Gradient Descent (SGD) computation is to distribute the randomly selected batch of inputs over multiple processors. To keep the distributed processors fully utilized requires…

Machine Learning · Computer Science 2020-01-06 Zhewei Yao , Amir Gholami , Daiyaan Arfeen , Richard Liaw , Joseph Gonzalez , Kurt Keutzer , Michael Mahoney

Data loading can dominate deep neural network training time on large-scale systems. We present a comprehensive study on accelerating data loading performance in large-scale distributed training. We first identify performance and scalability…

Machine Learning · Computer Science 2020-02-20 Chih-Chieh Yang , Guojing Cong

Humans learn continually throughout their lifespan by accumulating diverse knowledge and fine-tuning it for future tasks. When presented with a similar goal, neural networks suffer from catastrophic forgetting if data distributions across…

Machine Learning · Computer Science 2022-09-19 Dupati Srikar Chandra , Sakshi Varshney , P. K. Srijith , Sunil Gupta

In this paper, we propose a generic and simple strategy for utilizing stochastic gradient information in optimization. The technique essentially contains two consecutive steps in each iteration: 1) computing and normalizing each block…

Machine Learning · Computer Science 2018-04-24 Adams Wei Yu , Lei Huang , Qihang Lin , Ruslan Salakhutdinov , Jaime Carbonell

Sparse neural networks are a key factor in developing resource-efficient machine learning applications. We propose the novel and powerful sparse learning method Adaptive Regularized Training (ART) to compress dense into sparse networks.…

Computer Vision and Pattern Recognition · Computer Science 2023-08-17 Patrick Glandorf , Timo Kaiser , Bodo Rosenhahn

Training deep neural networks (DNNs) is computationally expensive, which is problematic especially when performing duplicated or similar training runs in model ensemble or fine-tuning pre-trained models, for example. Once we have trained…

Machine Learning · Computer Science 2023-10-04 Daiki Chijiwa

Current state-of-the-art visual recognition systems usually rely on the following pipeline: (a) pretraining a neural network on a large-scale dataset (e.g., ImageNet) and (b) finetuning the network weights on a smaller, task-specific…

Computer Vision and Pattern Recognition · Computer Science 2021-04-01 Guangrun Wang , Liang Lin , Rongcong Chen , Guangcong Wang , Jiqi Zhang

In this paper, we propose the nonlinearity generation method to speed up and stabilize the training of deep convolutional neural networks. The proposed method modifies a family of activation functions as nonlinearity generators (NGs). NGs…

Machine Learning · Computer Science 2017-10-18 Yang Jiang , Zeyang Dou , Qun Hao , Jie Cao , Kun Gao , Xi Chen

Recent developments in large language models have sparked interest in efficient pretraining methods. Stagewise training approaches to improve efficiency, like gradual stacking and layer dropping (Reddi et al, 2023; Zhang & He, 2020), have…

Computation and Language · Computer Science 2024-10-15 Abhishek Panigrahi , Nikunj Saunshi , Kaifeng Lyu , Sobhan Miryoosefi , Sashank Reddi , Satyen Kale , Sanjiv Kumar

Effective training of deep neural networks can be challenging, and there remain many open questions on how to best learn these models. Recently developed methods to improve neural network training examine teaching: providing learned…

Machine Learning · Computer Science 2021-03-15 Aniruddh Raghu , Maithra Raghu , Simon Kornblith , David Duvenaud , Geoffrey Hinton

We provide a theoretical explanation for the effectiveness of gradient clipping in training deep neural networks. The key ingredient is a new smoothness condition derived from practical neural network training examples. We observe that…

Optimization and Control · Mathematics 2020-02-12 Jingzhao Zhang , Tianxing He , Suvrit Sra , Ali Jadbabaie

Developing scalable solutions for training Graph Neural Networks (GNNs) for link prediction tasks is challenging due to the high data dependencies which entail high computational cost and huge memory footprint. We propose a new method for…

Machine Learning · Computer Science 2022-01-11 Nasrullah Sheikh , Xiao Qin , Berthold Reinwald , Chuan Lei

Recently, several optimization methods have been successfully applied to the hyperparameter optimization of deep neural networks (DNNs). The methods work by modeling the joint distribution of hyperparameter values and corresponding error.…

Machine Learning · Computer Science 2016-08-02 Ilija Ilievski , Jiashi Feng

Deep neural networks have recently achieved state of the art performance thanks to new training algorithms for rapid parameter estimation and new regularization methods to reduce overfitting. However, in practice the network architecture…

Machine Learning · Computer Science 2016-03-04 Minyoung Kim , Luca Rigazio