English
Related papers

Related papers: Sinusoidal Initialization, Time for a New Start

200 papers

Inducing and leveraging sparse activations during training and inference is a promising avenue for improving the computational efficiency of deep networks, which is increasingly important as network sizes continue to grow and their…

Machine Learning · Computer Science 2024-02-27 Ilan Price , Nicholas Daultry Ball , Samuel C. H. Lam , Adam C. Jones , Jared Tanner

Automated machine learning (AutoML) methods improve upon existing models by optimizing various aspects of their design. While present methods focus on hyperparameters and neural network topologies, other aspects of neural network design can…

Machine Learning · Computer Science 2023-04-10 Garrett Bingham

The ability to train randomly initialised deep neural networks is known to depend strongly on the variance of the weight matrices and biases as well as the choice of nonlinear activation. Here we complement the existing geometric analysis…

Information Theory · Computer Science 2021-02-09 Jared Tanner , Giuseppe Ughi

We develop a new method for regularising neural networks. We learn a probability distribution over the activations of all layers of the model and then insert imputed values into the network during training. We obtain a posterior for an…

Machine Learning · Computer Science 2019-10-14 Matthew Willetts , Alexander Camuto , Stephen Roberts , Chris Holmes

Deep learning needs high-precision handling of forwarding signals, backpropagating errors, and updating weights. This is inherently required by the learning algorithm since the gradient descent learning rule relies on the chain product of…

Neural and Evolutionary Computing · Computer Science 2024-12-30 Yang Li , Wei Wang , Ming Wang , Chunmeng Dou , Zhengyu Ma , Huihui Zhou , Peng Zhang , Nicola Lepri , Xumeng Zhang , Qing Luo , Xiaoxin Xu , Guanhua Yang , Feng Zhang , Ling Li , Daniele Ielmini , Ming Liu

Multiplicative stochasticity such as Dropout improves the robustness and generalizability of deep neural networks. Here, we further demonstrate that always-on multiplicative stochasticity combined with simple threshold neurons are…

Machine Learning · Computer Science 2019-10-29 Georgios Detorakis , Sourav Dutta , Abhishek Khanna , Matthew Jerry , Suman Datta , Emre Neftci

Efficient inference of Deep Neural Networks (DNNs) is essential to making AI ubiquitous. Two important algorithmic techniques have shown promise for enabling efficient inference - sparsity and binarization. These techniques translate into…

Computer Vision and Pattern Recognition · Computer Science 2023-12-06 Sachit Kuhar , Alexey Tumanov , Judy Hoffman

Training Deep Neural Networks is complicated by the fact that the distribution of each layer's inputs changes during training, as the parameters of the previous layers change. This slows down the training by requiring lower learning rates…

Machine Learning · Computer Science 2015-03-03 Sergey Ioffe , Christian Szegedy

Binary neural networks improve computationally efficiency of deep models with a large margin. However, there is still a performance gap between a successful full-precision training and binary training. We bring some insights about why this…

Machine Learning · Computer Science 2020-04-22 Xinlin Li , Vahid Partovi Nia

Deep kernel learning combines the non-parametric flexibility of kernel methods with the inductive biases of deep learning architectures. We propose a novel deep kernel learning model and stochastic variational inference procedure which…

Machine Learning · Statistics 2016-11-03 Andrew Gordon Wilson , Zhiting Hu , Ruslan Salakhutdinov , Eric P. Xing

We develop a general duality between neural networks and compositional kernels, striving towards a better understanding of deep learning. We show that initial representations generated by common random initializations are sufficiently rich…

Machine Learning · Computer Science 2017-05-23 Amit Daniely , Roy Frostig , Yoram Singer

We study in this paper how to initialize the parameters of multinomial logistic regression (a fully connected layer followed with softmax and cross entropy loss), which is widely used in deep neural network (DNN) models for classification…

Computer Vision and Pattern Recognition · Computer Science 2018-09-18 Bowen Cheng , Rong Xiao , Yandong Guo , Yuxiao Hu , Jianfeng Wang , Lei Zhang

Activation functions play a key role in neural networks so it becomes fundamental to understand their advantages and disadvantages in order to achieve better performances. This paper will first introduce common types of non linear…

Machine Learning · Computer Science 2018-04-10 Dabal Pedamonti

A supervised learning approach is proposed for regularization of large inverse problems where the main operator is built from noisy data. This is germane to superresolution imaging via the sampling indicators of the inverse scattering…

Numerical Analysis · Mathematics 2025-08-22 Fatemeh Pourahmadian , Yang Xu

To theoretically understand the behavior of trained deep neural networks, it is necessary to study the dynamics induced by gradient methods from a random initialization. However, the nonlinear and compositional structure of these models…

Machine Learning · Computer Science 2021-12-21 Karl Hajjar , Lénaïc Chizat , Christophe Giraud

For most deep learning algorithms training is notoriously time consuming. Since most of the computation in training neural networks is typically spent on floating point multiplications, we investigate an approach to training that eliminates…

Machine Learning · Computer Science 2016-02-29 Zhouhan Lin , Matthieu Courbariaux , Roland Memisevic , Yoshua Bengio

Coordinate-based neural representations have shown significant promise as an alternative to discrete, array-based representations for complex low dimensional signals. However, optimizing a coordinate-based network from randomly initialized…

Computer Vision and Pattern Recognition · Computer Science 2021-03-24 Matthew Tancik , Ben Mildenhall , Terrance Wang , Divi Schmidt , Pratul P. Srinivasan , Jonathan T. Barron , Ren Ng

First-break picking is an essential step in seismic data processing. First arrivals should be picked by an expert. This is a time-consuming procedure and subjective to a certain degree, leading to different results for different operators.…

Neural network optimization remains one of the most consequential yet poorly understood challenges in modern AI research, where improvements in training algorithms can lead to enhanced feature learning in foundation models,…

Machine Learning · Computer Science 2025-12-23 Ansh Nagwekar

Asynchronous distributed algorithms are a popular way to reduce synchronization costs in large-scale optimization, and in particular for neural network training. However, for nonsmooth and nonconvex objectives, few convergence guarantees…

Optimization and Control · Mathematics 2020-07-14 Vyacheslav Kungurtsev , Malcolm Egan , Bapi Chatterjee , Dan Alistarh