English
Related papers

Related papers: How to Initialize your Network? Robust Initializat…

200 papers

In supervised learning, the regularization path is sometimes used as a convenient theoretical proxy for the optimization path of gradient descent initialized from zero. In this paper, we study a modification of the regularization path for…

Machine Learning · Computer Science 2023-08-10 Sebastian Neumayer , Lénaïc Chizat , Michael Unser

Continuous neural representations have recently emerged as a powerful and flexible alternative to classical discretized representations of signals. However, training them to capture fine details in multi-scale signals is difficult and…

Machine Learning · Computer Science 2022-10-06 Sifan Wang , Hanwen Wang , Jacob H. Seidman , Paris Perdikaris

We present algorithms for initializing a convolutional network coding scheme in networks that may contain cycles. An initialization process is needed if the network is unknown or if local encoding kernels are chosen randomly. During the…

Information Theory · Computer Science 2014-06-25 Maxim Lvov , Haim H. Permuter

Even though dense networks have lost importance today, they are still used as final logic elements. It could be shown that these dense networks can be simplified by the sparse graph interpretation. This in turn shows that the information…

Neural and Evolutionary Computing · Computer Science 2018-09-25 Thomas Pircher , Dominik Haspel , Eberhard Schlücker

Robustness to adversarial attacks was shown to require a larger model capacity, and thus a larger memory footprint. In this paper, we introduce an approach to obtain robust yet compact models by pruning randomly-initialized binary networks.…

Machine Learning · Computer Science 2022-10-18 Chen Liu , Ziqi Zhao , Sabine Süsstrunk , Mathieu Salzmann

Gradient-based algorithms for training ResNets typically require a forward pass of the input data, followed by back-propagating the objective gradient to update parameters, which are time-consuming for deep ResNets. To break the…

Machine Learning · Computer Science 2021-02-19 Qi Sun , Hexin Dong , Zewei Chen , Weizhen Dian , Jiacheng Sun , Yitong Sun , Zhenguo Li , Bin Dong

When fine-tuning Deep Neural Networks (DNNs) to new data, DNNs are prone to overwriting network parameters required for task-specific functionality on previously learned tasks, resulting in a loss of performance on those tasks. We propose…

Machine Learning · Computer Science 2025-01-22 Christopher Angelini , Nidhal Bouaynaya

Deep residual networks (ResNets) made a recent breakthrough in deep learning. The core idea of ResNets is to have shortcut connections between layers that allow the network to be much deeper while still being easy to optimize avoiding…

Computer Vision and Pattern Recognition · Computer Science 2018-04-30 Sam Leroux , Pavlo Molchanov , Pieter Simoens , Bart Dhoedt , Thomas Breuel , Jan Kautz

Deep neural networks have been shown to be very powerful modeling tools for many supervised learning tasks involving complex input patterns. However, they can also easily overfit to training set biases and label noises. In addition to…

Machine Learning · Computer Science 2019-05-07 Mengye Ren , Wenyuan Zeng , Bin Yang , Raquel Urtasun

This article derives and validates three principles for initialization and architecture selection in finite width graph neural networks (GNNs) with ReLU activations. First, we theoretically derive what is essentially the unique…

Machine Learning · Statistics 2023-06-21 Gage DeZoort , Boris Hanin

Pretraining and fine-tuning are central stages in modern machine learning systems. In practice, feature learning plays an important role across both stages: deep neural networks learn a broad range of useful features during pretraining and…

Weights initialization in deep neural networks have a strong impact on the speed of converge of the learning map. Recent studies have shown that in the case of random initializations, a chaos/order phase transition occur in the space of…

Machine Learning · Computer Science 2023-06-28 Carlos Cardona

We theoretically characterize gradient descent dynamics in deep linear networks trained at large width from random initialization and on large quantities of random data. Our theory captures the ``wider is better" effect of…

Machine Learning · Computer Science 2025-06-17 Blake Bordelon , Cengiz Pehlevan

Initialization plays a critical role in the training of deep neural networks (DNN). Existing initialization strategies mainly focus on stabilizing the training process to mitigate gradient vanish/explosion problems. However, these…

Machine Learning · Computer Science 2021-08-17 Haitao Mao , Xu Chen , Qiang Fu , Lun Du , Shi Han , Dongmei Zhang

Regularization is a set of techniques that are used to improve the generalization ability of deep neural networks. In this paper, we introduce weight compander (WC), a novel effective method to improve generalization by reparameterizing…

Machine Learning · Computer Science 2023-06-30 Rinor Cakaj , Jens Mehnert , Bin Yang

Learned inverse problem solvers exhibit remarkable performance in applications like image reconstruction tasks. These data-driven reconstruction methods often follow a two-step scheme. First, one trains the often neural network-based…

Finding parameters in a deep neural network (NN) that fit training data is a nonconvex optimization problem, but a basic first-order optimization method (gradient descent) finds a global optimizer with perfect fit (zero-loss) in many…

Machine Learning · Computer Science 2025-03-07 Zhiyan Ding , Shi Chen , Qin Li , Stephen Wright

We show how to adjust for the variance introduced by dropout with corrections to weight initialization and Batch Normalization, yielding higher accuracy. Though dropout can preserve the expected input to a neuron between train and test, the…

Machine Learning · Computer Science 2017-03-27 Dan Hendrycks , Kevin Gimpel

Neural networks are often over-parameterized and hence benefit from aggressive regularization. Conventional regularization methods, such as Dropout or weight decay, do not leverage the structures of the network's inputs and hidden states.…

Machine Learning · Computer Science 2021-01-07 Hieu Pham , Quoc V. Le

Binary neural networks (BNNs) have received ever-increasing popularity for their great capability of reducing storage burden as well as quickening inference time. However, there is a severe performance drop compared with real-valued…

Machine Learning · Computer Science 2023-02-07 Sheng Xu , Yanjing Li , Teli Ma , Mingbao Lin , Hao Dong , Baochang Zhang , Peng Gao , Jinhu Lv