English
Related papers

Related papers: Path-Normalized Optimization of Recurrent Neural N…

200 papers

In this article we study the stochastic gradient descent (SGD) optimization method in the training of fully-connected feedforward artificial neural networks with ReLU activation. The main result of this work proves that the risk of the SGD…

Numerical Analysis · Mathematics 2022-09-28 Arnulf Jentzen , Adrian Riekert

When optimizing a nonlinear objective, one can employ a neural network as a surrogate for the nonlinear function. However, the resulting optimization model can be time-consuming to solve globally with exact methods. As a result, local…

Optimization and Control · Mathematics 2026-03-19 Jiatai Tong , Yilin Zhu , Thiago Serra , Samuel Burer

Deep neural networks are often trained in the over-parametrized regime (i.e. with far more parameters than training examples), and understanding why the training converges to solutions that generalize remains an open problem. Several…

Machine Learning · Statistics 2018-03-23 Hartmut Maennel , Olivier Bousquet , Sylvain Gelly

Graph processes exhibit a temporal structure determined by the sequence index and and a spatial structure determined by the graph support. To learn from graph processes, an information processing architecture must then be able to exploit…

Signal Processing · Electrical Eng. & Systems 2020-12-02 Luana Ruiz , Fernando Gama , Alejandro Ribeiro

Training recurrent neural networks (RNNs) is a hard problem due to degeneracies in the optimization landscape, a problem also known as vanishing/exploding gradients. Short of designing new RNN architectures, previous methods for dealing…

Neural and Evolutionary Computing · Computer Science 2020-02-11 A. Emin Orhan , Xaq Pitkow

Recurrent Neural Networks (RNNs) achieve state-of-the-art results in many sequence-to-sequence modeling tasks. However, RNNs are difficult to train and tend to suffer from overfitting. Motivated by the Data Processing Inequality (DPI), we…

Machine Learning · Statistics 2018-05-24 Ziv Aharoni , Gal Rattner , Haim Permuter

The first provably efficient algorithm for learning graph neural networks (GNNs) with one hidden layer for node information convolution is provided in this paper. Two types of GNNs are investigated, depending on whether labels are attached…

Machine Learning · Computer Science 2020-12-08 Qunwei Li , Shaofeng Zou , Wenliang Zhong

This paper studies the performance of a recently proposed preconditioned stochastic gradient descent (PSGD) algorithm on recurrent neural network (RNN) training. PSGD adaptively estimates a preconditioner to accelerate gradient descent, and…

Machine Learning · Statistics 2016-12-09 Xi-Lin Li

Deep neural networks have recently demonstrated the traffic prediction capability with the time series data obtained by sensors mounted on road segments. However, capturing spatio-temporal features of the traffic data often requires a…

Machine Learning · Computer Science 2019-02-19 Youngjoo Kim , Peng Wang , Lyudmila Mihaylova

Rectified Linear Units (ReLU) have become the main model for the neural units in current deep learning systems. This choice has been originally suggested as a way to compensate for the so called vanishing gradient problem which can undercut…

Disordered Systems and Neural Networks · Physics 2024-05-06 Carlo Baldassi , Enrico M. Malatesta , Riccardo Zecchina

Training recurrent neural networks (RNNs) is a high-dimensional process that requires updating numerous parameters. Therefore, it is often difficult to pinpoint the underlying learning mechanisms. To address this challenge, we propose to…

Neurons and Cognition · Quantitative Biology 2025-02-12 Udith Haputhanthri , Liam Storan , Yiqi Jiang , Tarun Raheja , Adam Shai , Orhun Akengin , Nina Miolane , Mark J. Schnitzer , Fatih Dinc , Hidenori Tanaka

Recurrent Neural Networks (RNNs) offer fast inference on long sequences but are hard to optimize and slow to train. Deep state-space models (SSMs) have recently been shown to perform remarkably well on long sequence modeling tasks, and have…

Machine Learning · Computer Science 2023-03-14 Antonio Orvieto , Samuel L Smith , Albert Gu , Anushan Fernando , Caglar Gulcehre , Razvan Pascanu , Soham De

Gradient descent (GD) type optimization methods are the standard instrument to train artificial neural networks (ANNs) with rectified linear unit (ReLU) activation. Despite the great success of GD type optimization methods in numerical…

Optimization and Control · Mathematics 2022-12-29 Arnulf Jentzen , Adrian Riekert

Kernel normalization methods have been employed to improve robustness of optimization methods to reparametrization of convolution kernels, covariate shift, and to accelerate training of Convolutional Neural Networks (CNNs). However, our…

Computer Vision and Pattern Recognition · Computer Science 2016-10-25 Mete Ozay , Takayuki Okatani

We propose and analyze a new family of algorithms for training neural networks with ReLU activations. Our algorithms are based on the technique of alternating minimization: estimating the activation patterns of each ReLU for all given…

Machine Learning · Computer Science 2018-10-12 Gauri Jagatap , Chinmay Hegde

We propose a novel variant of SGD customized for training network architectures that support anytime behavior: such networks produce a series of increasingly accurate outputs over time. Efficient architectural designs for these networks…

Machine Learning · Computer Science 2020-08-18 Chengcheng Wan , Henry Hoffmann , Shan Lu , Michael Maire

We consider training over-parameterized two-layer neural networks with Rectified Linear Unit (ReLU) using gradient descent (GD) method. Inspired by a recent line of work, we study the evolutions of network prediction errors across GD…

Machine Learning · Computer Science 2019-09-04 Lili Su , Pengkun Yang

The presented work demonstrates the training of recurrent neural networks (RNNs) from distributions of atom coordinates in solid state structures that were obtained using ab initio molecular dynamics (AIMD) simulations. AIMD simulations on…

Computational Physics · Physics 2019-09-27 Mohammad Javad Eslamibidgoli , Mehrdad Mokhtari , Michael H. Eikerling

Graph neural networks (GNNs) work remarkably well in semi-supervised node regression, yet a rigorous theory explaining when and why they succeed remains lacking. To address this gap, we study an aggregate-and-readout model that encompasses…

Machine Learning · Statistics 2026-02-20 Juntong Chen , Claire Donnat , Olga Klopp , Johannes Schmidt-Hieber

Several variants of recurrent neural networks (RNNs) with orthogonal or unitary recurrent matrices have recently been developed to mitigate the vanishing/exploding gradient problem and to model long-term dependencies of sequences. However,…

Machine Learning · Computer Science 2019-11-20 Kyle Helfrich , Qiang Ye