English
Related papers

Related papers: Sample Variance Decay in Randomly Initialized ReLU…

200 papers

Recent works have shown that on sufficiently over-parametrized neural nets, gradient descent with relatively large initialization optimizes a prediction function in the RKHS of the Neural Tangent Kernel (NTK). This analysis leads to global…

Machine Learning · Statistics 2020-04-28 Colin Wei , Jason D. Lee , Qiang Liu , Tengyu Ma

Neural networks have been very successful in many applications; we often, however, lack a theoretical understanding of what the neural networks are actually learning. This problem emerges when trying to generalise to new data sets. The…

Classical Analysis and ODEs · Mathematics 2022-11-22 Matthew Thorpe , Yves van Gennip

Deep artificial neural networks achieve surprising generalization abilities that remain poorly understood. In this paper, we present a new approach to analyzing generalization for deep feed-forward ReLU networks that takes advantage of the…

Machine Learning · Computer Science 2023-07-06 Ramchandran Muthukumar , Jeremias Sulam

We investigate filter level sparsity that emerges in convolutional neural networks (CNNs) which employ Batch Normalization and ReLU activation, and are trained with adaptive gradient descent techniques and L2 regularization or weight decay.…

Machine Learning · Computer Science 2019-04-08 Dushyant Mehta , Kwang In Kim , Christian Theobalt

Stochastic gradient descent with a large initial learning rate is widely used for training modern neural net architectures. Although a small initial learning rate allows for faster training and better test performance initially, the large…

Machine Learning · Computer Science 2020-04-28 Yuanzhi Li , Colin Wei , Tengyu Ma

We introduce and analyze a new technique for model reduction for deep neural networks. While large networks are theoretically capable of learning arbitrarily complex models, overfitting and model redundancy negatively affects the prediction…

Machine Learning · Computer Science 2017-11-27 Alireza Aghasi , Afshin Abdi , Nam Nguyen , Justin Romberg

Empirical works show that for ReLU neural networks (NNs) with small initialization, input weights of hidden neurons (the input weight of a hidden neuron consists of the weight from its input layer to the hidden neuron and its bias term)…

Machine Learning · Computer Science 2022-10-20 Hanxu Zhou , Qixuan Zhou , Tao Luo , Yaoyu Zhang , Zhi-Qin John Xu

We discovered that the neural networks, especially the deep ReLU networks, demonstrate an `over-generalization' phenomenon. That is, the output values for the inputs that were not seen during training are mapped close to the output range…

Machine Learning · Computer Science 2024-10-23 Harsh Shrivastava

A significant advance in accelerating neural network training has been the development of normalization methods, permitting the training of deep models both faster and with better accuracy. These advances come with practical challenges: for…

Machine Learning · Computer Science 2019-03-05 Jasmine Collins , Johannes Balle , Jonathon Shlens

This paper first answers the question "why do the two most powerful techniques Dropout and Batch Normalization (BN) often lead to a worse performance when they are combined together?" in both theoretical and statistical aspects.…

Machine Learning · Computer Science 2018-01-17 Xiang Li , Shuo Chen , Xiaolin Hu , Jian Yang

We introduce an algorithm where the individual bits representing the weights of a neural network are learned. This method allows training weights with integer values on arbitrary bit-depths and naturally uncovers sparse networks, without…

Machine Learning · Computer Science 2022-02-22 Cristian Ivan

We study the problem of training deep neural networks with Rectified Linear Unit (ReLU) activation function using gradient descent and stochastic gradient descent. In particular, we study the binary classification problem and show that for…

Machine Learning · Computer Science 2018-12-31 Difan Zou , Yuan Cao , Dongruo Zhou , Quanquan Gu

This work theoretically studies stochastic neural networks, a main type of neural network in use. We prove that as the width of an optimized stochastic neural network tends to infinity, its predictive variance on the training set decreases…

Machine Learning · Computer Science 2022-05-25 Liu Ziyin , Hanlin Zhang , Xiangming Meng , Yuting Lu , Eric Xing , Masahito Ueda

In many information processing systems, it may be desirable to ensure that any change of the input, whether by shifting or scaling, results in a corresponding change in the system response. While deep neural networks are gradually replacing…

Computer Vision and Pattern Recognition · Computer Science 2024-02-22 Sébastien Herbreteau , Emmanuel Moebel , Charles Kervrann

Recent work has explored the possibility of pruning neural networks at initialization. We assess proposals for doing so: SNIP (Lee et al., 2019), GraSP (Wang et al., 2020), SynFlow (Tanaka et al., 2020), and magnitude pruning. Although…

Machine Learning · Computer Science 2021-03-23 Jonathan Frankle , Gintare Karolina Dziugaite , Daniel M. Roy , Michael Carbin

Convex $\ell_1$ regularization using an infinite dictionary of neurons has been suggested for constructing neural networks with desired approximation guarantees, but can be affected by an arbitrary amount of over-parametrization. This can…

Optimization and Control · Mathematics 2022-06-01 Konstantin Pieper , Armenak Petrosyan

Recurrent neural networks are deep learning topologies that can be trained to classify long documents. However, in our recent work, we found a critical problem with these cells: they can use the length differences between texts of different…

Machine Learning · Computer Science 2022-12-19 Jean-Thomas Baillargeon , Hélène Cossette , Luc Lamontagne

Neural networks are very successful tools in for example advanced classification. From a statistical point of view, fitting a neural network may be seen as a kind of regression, where we seek a function from the input space to a space of…

Machine Learning · Statistics 2021-07-06 Anton Johansson , Niklas Engsner , Claes Strannegård , Petter Mostad

Continual learning entails learning a sequence of tasks and balancing their knowledge appropriately. With limited access to old training samples, much of the current work in deep neural networks has focused on overcoming catastrophic…

Machine Learning · Computer Science 2023-10-16 Yilin Lyu , Liyuan Wang , Xingxing Zhang , Zicheng Sun , Hang Su , Jun Zhu , Liping Jing

In this paper, we consider one dimensional (shallow) ReLU neural networks in which weights are chosen randomly and only the terminal layer is trained. First, we mathematically show that for such networks L2-regularized regression…

Machine Learning · Computer Science 2023-10-05 Jakob Heiss , Josef Teichmann , Hanna Wutte
‹ Prev 1 4 5 6 7 8 10 Next ›