English
Related papers

Related papers: Correspondence between neuroevolution and gradient…

200 papers

We introduce a principled method to train end-to-end analog neural networks by stochastic gradient descent. In these analog neural networks, the weights to be adjusted are implemented by the conductances of programmable resistive devices…

Neural and Evolutionary Computing · Computer Science 2020-06-11 Jack Kendall , Ross Pantone , Kalpana Manickavasagam , Yoshua Bengio , Benjamin Scellier

We analyze speed of convergence to global optimum for gradient descent training a deep linear neural network (parameterized as $x \mapsto W_N W_{N-1} \cdots W_1 x$) by minimizing the $\ell_2$ loss over whitened data. Convergence at a linear…

Machine Learning · Computer Science 2019-10-29 Sanjeev Arora , Nadav Cohen , Noah Golowich , Wei Hu

Learning rates in stochastic neural network training are currently determined a priori to training, using expensive manual or automated iterative tuning. This study proposes gradient-only line searches to resolve the learning rate for…

Machine Learning · Statistics 2020-01-16 Dominic Kafka , Daniel N. Wilke

In recent years, much work have studied the use of convolutional neural networks for gravitational-wave detection. However little work pay attention to whether the transient noise can trigger the CNN model or not. In this paper, we study…

General Relativity and Quantum Cosmology · Physics 2021-03-08 Chao Zhan , Mingzhen Jia , Cunliang Ma , Zhongliang Lu , Wenbin Lin

We study the convergence properties of gradient descent for training deep linear neural networks, i.e., deep matrix factorizations, by extending a previous analysis for the related gradient flow. We show that under suitable conditions on…

Machine Learning · Computer Science 2021-11-25 Gabin Maxime Nguegnang , Holger Rauhut , Ulrich Terstiege

We analyze the training dynamics for deep linear networks using a new metric - layer imbalance - which defines the flatness of a solution. We demonstrate that different regularization methods, such as weight decay or noise data…

Machine Learning · Computer Science 2020-07-21 Boris Ginsburg

The infinitely wide neural network has been proven a useful and manageable mathematical model that enables the understanding of many phenomena appearing in deep learning. One example is the convergence of random deep networks to Gaussian…

Machine Learning · Statistics 2024-03-19 Thiziri Nait-Saada , Alireza Naderi , Jared Tanner

Neuroevolution methods evolve the weights of a neural network, and in some cases the topology, but little work has been done to analyze the effect of evolving the activation functions of individual nodes on network size, which is important…

Neural and Evolutionary Computing · Computer Science 2017-03-22 Alexander Hagg , Maximilian Mensing , Alexander Asteroth

We demonstrate that the dynamics of neural networks trained with gradient descent and the dynamics of scalar fields in a flat, vacuum energy dominated Universe are structurally profoundly related. This duality provides the framework for…

General Relativity and Quantum Cosmology · Physics 2022-02-24 Sven Krippendorf , Michael Spannowsky

Symmetries are prevalent in deep learning and can significantly influence the learning dynamics of neural networks. In this paper, we examine how exponential symmetries -- a broad subclass of continuous symmetries present in the model…

Machine Learning · Computer Science 2024-11-08 Liu Ziyin , Mingze Wang , Hongchao Li , Lei Wu

The stochastic gradient descent (SGD) method is most widely used for deep neural network (DNN) training. However, the method does not always converge to a flat minimum of the loss surface that can demonstrate high generalization capability.…

Machine Learning · Computer Science 2020-09-08 Wonyong Sung , Iksoo Choi , Jinhwan Park , Seokhyun Choi , Sungho Shin

We prove that if an activation function satisfies some mild conditions and number of neurons in a two-layered fully connected neural network with this activation function is beyond a certain threshold, then gradient descent on quadratic…

Optimization and Control · Mathematics 2019-11-14 Biswarup Das , Eugene. A. Golikov

We investigate the stationary (late-time) training regime of single- and two-layer underparameterized linear neural networks within the continuum limit of stochastic gradient descent (SGD) for synthetic Gaussian data. In the case of a…

Machine Learning · Computer Science 2024-07-30 Markus Gross , Arne P. Raulf , Christoph Räth

We showcase important features of the dynamics of the Stochastic Gradient Descent (SGD) in the training of neural networks. We present empirical observations that commonly used large step sizes (i) lead the iterates to jump from one side of…

Machine Learning · Computer Science 2023-06-08 Maksym Andriushchenko , Aditya Varre , Loucas Pillaud-Vivien , Nicolas Flammarion

In this paper, we provide the first precise distributional characterization of gradient descent iterates for general multi-layer neural networks under the canonical single-index regression model, in the `finite-width proportional regime'…

Machine Learning · Computer Science 2025-05-09 Qiyang Han , Masaaki Imaizumi

Adding noises to artificial neural network(ANN) has been shown to be able to improve robustness in previous work. In this work, we propose a new technique to compute the pathwise stochastic gradient estimate with respect to the standard…

Machine Learning · Computer Science 2021-02-10 Li Xiao , Zeliang Zhang , Yijie Peng

We propose stochastic, non-parametric activation functions that are fully learnable and individual to each neuron. Complexity and the risk of overfitting are controlled by placing a Gaussian process prior over these functions. The result is…

Machine Learning · Statistics 2017-12-01 Sebastian Urban , Marcus Basalla , Patrick van der Smagt

Recent research shows that when Gradient Descent (GD) is applied to neural networks, the loss almost never decreases monotonically. Instead, the loss oscillates as gradient descent converges to its ''Edge of Stability'' (EoS). Here, we find…

Machine Learning · Computer Science 2023-05-23 Itai Kreisler , Mor Shpigel Nacson , Daniel Soudry , Yair Carmon

A surprising phenomenon in the training of neural networks is the ability of gradient descent to find global minimizers of the training loss despite its non-convexity. Following earlier works, we investigate this behavior for wide shallow…

Optimization and Control · Mathematics 2026-05-12 Romain Petit , Clarice Poon , Gabriel Peyré

Sparsification of neural networks is one of the effective complexity reduction methods to improve efficiency and generalizability. Binarized activation offers an additional computational saving for inference. Due to vanishing gradient issue…

Optimization and Control · Mathematics 2019-02-12 Thu Dinh , Jack Xin
‹ Prev 1 4 5 6 7 8 10 Next ›