English
Related papers

Related papers: Stacking as Accelerated Gradient Descent

200 papers

Deep neural networks are capable of modelling highly non-linear functions by capturing different levels of abstraction of data hierarchically. While training deep networks, first the system is initialized near a good optimum by greedy…

Machine Learning · Computer Science 2016-03-10 Anirban Santara , Debapriya Maji , DP Tejas , Pabitra Mitra , Arobinda Gupta

Adaptive inference is a promising technique to improve the computational efficiency of deep models at test time. In contrast to static models which use the same computation graph for all instances, adaptive networks can dynamically adjust…

Computer Vision and Pattern Recognition · Computer Science 2019-08-20 Hao Li , Hong Zhang , Xiaojuan Qi , Ruigang Yang , Gao Huang

We study learning properties of accelerated gradient descent methods for linear least-squares in Hilbert spaces. We analyze the implicit regularization properties of Nesterov acceleration and a variant of heavy-ball in terms of…

Machine Learning · Computer Science 2019-12-17 Nicolò Pagliana , Lorenzo Rosasco

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

Neural networks are typically trained with a single learning rate across all layers. While recent empirical evidence suggests that assigning layer-specific learning rates can accelerate training, a principled understanding of the conditions…

Machine Learning · Computer Science 2026-05-26 Sihan Zeng , Sujay Bhatt , Sumitra Ganesh

We propose an incremental training method that partitions the original network into sub-networks, which are then gradually incorporated in the running network during the training process. To allow for a smooth dynamic growth of the network,…

Machine Learning · Computer Science 2018-03-29 Roxana Istrate , Adelmo Cristiano Innocenza Malossi , Costas Bekas , Dimitrios Nikolopoulos

To parse images into fine-grained semantic parts, the complex fine-grained elements will put it in trouble when using off-the-shelf semantic segmentation networks. In this paper, for image parsing task, we propose to parse images from…

Computer Vision and Pattern Recognition · Computer Science 2018-04-24 Jiagao Hu , Zhengxing Sun , Yunhan Sun , Jinlong Shi

Spiking neural networks are biologically plausible counterparts of the artificial neural networks, artificial neural networks are usually trained with stochastic gradient descent and spiking neural networks are trained with spike timing…

Neural and Evolutionary Computing · Computer Science 2019-09-26 Ruthvik Vaila , John Chiasson , Vishal Saxena

Deep neural networks have yielded superior performance in many applications; however, the gradient computation in a deep model with millions of instances lead to a lengthy training process even with modern GPU/TPU hardware acceleration. In…

Machine Learning · Computer Science 2019-05-10 Jiong Zhang , Hsiang-fu Yu , Inderjit S. Dhillon

The vast majority of successful deep neural networks are trained using variants of stochastic gradient descent (SGD) algorithms. Recent attempts to improve SGD can be broadly categorized into two approaches: (1) adaptive learning rate…

Machine Learning · Computer Science 2019-12-04 Michael R. Zhang , James Lucas , Geoffrey Hinton , Jimmy Ba

Nesterov's accelerated gradient descent method (AGD) is a seminal deterministic first-order method known to achieve the optimal order of iteration complexity for solving convex smooth optimization problems. Two distinct sequences of…

Optimization and Control · Mathematics 2026-03-10 Yan Wu , Yipeng Zhang , Lu Liu , Yuyuan Ouyang

The brain is the perfect place to look for inspiration to develop more efficient neural networks. The inner workings of our synapses and neurons provide a glimpse at what the future of deep learning might look like. This paper serves as a…

Neural and Evolutionary Computing · Computer Science 2023-08-15 Jason K. Eshraghian , Max Ward , Emre Neftci , Xinxin Wang , Gregor Lenz , Girish Dwivedi , Mohammed Bennamoun , Doo Seok Jeong , Wei D. Lu

The development of machine learning is promoting the search for fast and stable minimization algorithms. To this end, we suggest a change in the current gradient descent methods that should speed up the motion in flat regions and slow it…

Machine Learning · Computer Science 2019-06-13 Marco Baiesi

Policy gradient methods are widely used in reinforcement learning algorithms to search for better policies in the parameterized policy space. They do gradient search in the policy space and are known to converge very slowly. Nesterov…

Machine Learning · Computer Science 2018-04-26 K. Lakshmanan

Deep reinforcement learning has achieved many impressive results in recent years. However, tasks with sparse rewards or long horizons continue to pose significant challenges. To tackle these important problems, we propose a general…

Artificial Intelligence · Computer Science 2017-04-12 Carlos Florensa , Yan Duan , Pieter Abbeel

Much of studies on neural computation are based on network models of static neurons that produce analog output, despite the fact that information processing in the brain is predominantly carried out by dynamic neurons that produce discrete…

Neurons and Cognition · Quantitative Biology 2017-06-21 Dongsung Huh , Terrence J. Sejnowski

Stacked denoising auto encoders (DAEs) are well known to learn useful deep representations, which can be used to improve supervised training by initializing a deep network. We investigate a training scheme of a deep DAE, where DAE layers…

Machine Learning · Computer Science 2015-04-14 Alexander Kalmanovich , Gal Chechik

Deep learning has revolutionized industries like computer vision, natural language processing, and speech recognition. However, back propagation, the main method for training deep neural networks, faces challenges like computational…

Machine Learning · Computer Science 2023-08-15 Gokulprasath R

Stochastic methods with coordinate-wise adaptive stepsize (such as RMSprop and Adam) have been widely used in training deep neural networks. Despite their fast convergence, they can generalize worse than stochastic gradient descent. In this…

Machine Learning · Computer Science 2019-05-27 Shuai Zheng , James T. Kwok

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
‹ Prev 1 4 5 6 7 8 10 Next ›