English
Related papers

Related papers: How to Start Training: The Effect of Initializatio…

200 papers

Current research suggests that the key factors in designing neural network architectures involve choosing number of filters for every convolution layer, number of hidden neurons for every fully connected layer, dropout and pruning. The…

Machine Learning · Computer Science 2020-09-17 Himanshu Pradeep Aswani , Amit Sethi

Deep neural networks are usually initialized with random weights, with adequately selected initial variance to ensure stable signal propagation during training. However, selecting the appropriate variance becomes challenging especially as…

Machine Learning · Computer Science 2022-11-07 Jiawei Zhao , Florian Schäfer , Anima Anandkumar

The training process of neural networks usually optimize weights and bias parameters of linear transformations, while nonlinear activation functions are pre-specified and fixed. This work develops a systematic approach to constructing…

Machine Learning · Computer Science 2024-10-29 Zhengqi Liu , Shuhao Cao , Yuwen Li , Ludmil Zikatanov

Empirical studies suggest that machine learning models often rely on features, such as the background, that may be spuriously correlated with the label only during training time, resulting in poor accuracy during test-time. In this work, we…

Machine Learning · Computer Science 2024-09-10 Vaishnavh Nagarajan , Anders Andreassen , Behnam Neyshabur

Neural networks are often trained on multiple tasks, either simultaneously (multi-task learning, MTL) or sequentially (pretraining and subsequent finetuning, PT+FT). In particular, it is common practice to pretrain neural networks on a…

Machine Learning · Computer Science 2024-11-04 Samuel Lippl , Jack W. Lindsey

Activation function is crucial to the recent successes of deep neural networks. In this paper, we first propose a new activation function, Multiple Parametric Exponential Linear Units (MPELU), aiming to generalize and unify the rectified…

Computer Vision and Pattern Recognition · Computer Science 2017-01-18 Yang Li , Chunxiao Fan , Yong Li , Qiong Wu , Yue Ming

We study the gradient-based training of large-depth residual networks (ResNets) from standard random initializations. We show that infinite-depth ResNets behave as if they were infinitely wide, regardless of their actual width. More…

Machine Learning · Computer Science 2026-03-04 Lénaïc Chizat

Understanding how large neural networks avoid memorizing training data is key to explaining their high generalization performance. To examine the structure of when and where memorization occurs in a deep network, we use a recently developed…

Machine Learning · Computer Science 2021-06-01 Cory Stephenson , Suchismita Padhy , Abhinav Ganesh , Yue Hui , Hanlin Tang , SueYeon Chung

Hypernetworks are meta neural networks that generate weights for a main neural network in an end-to-end differentiable manner. Despite extensive applications ranging from multi-task learning to Bayesian deep learning, the problem of…

Machine Learning · Computer Science 2023-12-15 Oscar Chang , Lampros Flokas , Hod Lipson

How can local-search methods such as stochastic gradient descent (SGD) avoid bad local minima in training multi-layer neural networks? Why can they fit random labels even given non-convex and non-smooth architectures? Most existing theory…

Machine Learning · Computer Science 2019-05-28 Zeyuan Allen-Zhu , Yuanzhi Li , Zhao Song

Deep neural networks, particularly those employing Rectified Linear Units (ReLU), are often perceived as complex, high-dimensional, non-linear systems. This complexity poses a significant challenge to understanding their internal learning…

Machine Learning · Computer Science 2025-11-11 Longqing Ye

Artificial neural networks can acquire many aspects of human knowledge from data, making them promising as models of human learning. But what those networks can learn depends upon their inductive biases -- the factors other than the data…

Machine Learning · Computer Science 2025-02-28 Gianluca Bencomo , Max Gupta , Ioana Marinescu , R. Thomas McCoy , Thomas L. Griffiths

In adversarial attacks to machine-learning classifiers, small perturbations are added to input that is correctly classified. The perturbations yield adversarial examples, which are virtually indistinguishable from the unperturbed input, and…

Machine Learning · Statistics 2018-09-26 Luca de Alfaro

The training success, training speed and generalization ability of neural networks rely crucially on the choice of random parameter initialization. It has been shown for multiple architectures that initial dynamical isometry is particularly…

Machine Learning · Computer Science 2022-10-06 Advait Gadhikar , Rebekka Burkholz

In past few years, various initialization schemes have been proposed. These schemes are glorot initialization, He initialization, initialization using orthogonal matrix, random walk method for initialization. Some of these methods stress on…

Machine Learning · Computer Science 2025-09-08 Vijay Pandey

Neural network training is inherently sensitive to initialization and the randomness induced by stochastic gradient descent. However, it is unclear to what extent such effects lead to meaningfully different networks, either in terms of the…

Machine Learning · Computer Science 2025-06-17 Devin Kwok , Gül Sena Altıntaş , Colin Raffel , David Rolnick

Gradient-based methods for the distributed training of residual networks (ResNets) typically require a forward pass of the input data, followed by back-propagating the error gradient to update model parameters, which becomes time-consuming…

Machine Learning · Computer Science 2021-12-13 Qi Sun , Hexin Dong , Zewei Chen , Jiacheng Sun , Zhenguo Li , Bin Dong

We consider the problem of learning an unknown ReLU network with respect to Gaussian inputs and obtain the first nontrivial results for networks of depth more than two. We give an algorithm whose running time is a fixed polynomial in the…

Machine Learning · Computer Science 2020-09-29 Sitan Chen , Adam R. Klivans , Raghu Meka

For fast and energy-efficient deployment of trained deep neural networks on resource-constrained embedded hardware, each learned weight parameter should ideally be represented and stored using a single bit. Error-rates usually increase when…

Machine Learning · Computer Science 2018-02-27 Mark D. McDonnell

Training deep neural networks is a challenging non-convex optimization problem. Recent work has proven that the strong duality holds (which means zero duality gap) for regularized finite-width two-layer ReLU networks and consequently…

Machine Learning · Computer Science 2023-03-08 Yifei Wang , Tolga Ergen , Mert Pilanci