English
Related papers

Related papers: When Expressivity Meets Trainability: Fewer than $…

200 papers

For a certain scaling of the initialization of stochastic gradient descent (SGD), wide neural networks (NN) have been shown to be well approximated by reproducing kernel Hilbert space (RKHS) methods. Recent empirical work showed that, for…

Machine Learning · Statistics 2022-01-12 Behrooz Ghorbani , Song Mei , Theodor Misiakiewicz , Andrea Montanari

The fundamental learning theory behind neural networks remains largely open. What classes of functions can neural networks actually learn? Why doesn't the trained network overfit when it is overparameterized? In this work, we prove that…

Machine Learning · Computer Science 2020-06-02 Zeyuan Allen-Zhu , Yuanzhi Li , Yingyu Liang

There has been a lot of recent interest in trying to characterize the error surface of deep models. This stems from a long standing question. Given that deep networks are highly nonlinear systems optimized by local gradient methods, why do…

Machine Learning · Statistics 2017-02-20 Grzegorz Swirszcz , Wojciech Marian Czarnecki , Razvan Pascanu

There are two widely known issues with properly training Recurrent Neural Networks, the vanishing and the exploding gradient problems detailed in Bengio et al. (1994). In this paper we attempt to improve the understanding of the underlying…

Machine Learning · Computer Science 2013-02-19 Razvan Pascanu , Tomas Mikolov , Yoshua Bengio

It is shown that for deep neural networks, a single wide layer of width $N+1$ ($N$ being the number of training samples) suffices to prove the connectivity of sublevel sets of the training loss function. In the two-layer setting, the same…

Machine Learning · Computer Science 2021-01-22 Quynh Nguyen

One of the major concerns for neural network training is that the non-convexity of the associated loss functions may cause bad landscape. The recent success of neural networks suggests that their loss landscape is not too bad, but what…

Machine Learning · Computer Science 2023-07-19 Ruoyu Sun , Dawei Li , Shiyu Liang , Tian Ding , R Srikant

The optimization problem behind neural networks is highly non-convex. Training with stochastic gradient descent and variants requires careful parameter tuning and provides no guarantee to achieve the global optimum. In contrast we show…

Machine Learning · Computer Science 2016-10-31 Antoine Gautier , Quynh Nguyen , Matthias Hein

Can a neural network minimizing cross-entropy learn linearly separable data? Despite progress in the theory of deep learning, this question remains unsolved. Here we prove that SGD globally optimizes this learning problem for a two-layer…

Machine Learning · Computer Science 2021-07-29 Roei Sarussi , Alon Brutzkus , Amir Globerson

Training neural networks requires significant computational resources and energy. Methods like mixed-precision and quantization-aware training reduce bit usage, yet they still depend heavily on computationally expensive gradient-based…

Machine Learning · Computer Science 2025-09-30 Noa Cohen , Omkar Joglekar , Dotan Di Castro , Vladimir Tchuiev , Shir Kozlovsky , Michal Moshkovitz

We study the training dynamics of shallow neural networks, in a two-timescale regime in which the stepsizes for the inner layer are much smaller than those for the outer layer. In this regime, we prove convergence of the gradient flow to a…

Optimization and Control · Mathematics 2023-10-26 Pierre Marion , Raphaël Berthier

As deep neural networks grow in size, from thousands to millions to billions of weights, the performance of those networks becomes limited by our ability to accurately train them. A common naive question arises: if we have a system with…

Machine Learning · Computer Science 2018-05-29 Nathan O. Hodas , Panos Stinis

Neural Networks accomplish amazing things, but they suffer from computational and memory bottlenecks that restrict their usage. Nowhere can this be better seen than in the mobile space, where specialized hardware is being created just to…

Computer Vision and Pattern Recognition · Computer Science 2019-04-15 Jon Hoffman

We consider gradient-based optimisation of wide, shallow neural networks, where the output of each hidden node is scaled by a positive parameter. The scaling parameters are non-identical, differing from the classical Neural Tangent Kernel…

Machine Learning · Statistics 2025-02-19 Francois Caron , Fadhel Ayed , Paul Jung , Hoil Lee , Juho Lee , Hongseok Yang

Training neural networks involves solving large-scale non-convex optimization problems. This task has long been believed to be extremely difficult, with fear of local minima and other obstacles motivating a variety of schemes to improve…

Neural and Evolutionary Computing · Computer Science 2015-05-25 Ian J. Goodfellow , Oriol Vinyals , Andrew M. Saxe

It is well-known that neural networks are computationally hard to train. On the other hand, in practice, modern day neural networks are trained efficiently using SGD and a variety of tricks that include different activation functions (e.g.…

Machine Learning · Computer Science 2014-10-29 Roi Livni , Shai Shalev-Shwartz , Ohad Shamir

State-of-the-art training algorithms for deep learning models are based on stochastic gradient descent (SGD). Recently, many variations have been explored: perturbing parameters for better accuracy (such as in Extragradient), limiting SGD…

Machine Learning · Computer Science 2022-03-23 Amirkeivan Mohtashami , Martin Jaggi , Sebastian U. Stich

It has been observed that design choices of neural networks are often crucial for their successful optimization. In this article, we therefore discuss the question if it is always possible to redesign a neural network so that it trains well…

Machine Learning · Computer Science 2020-07-28 G. Welper

We analyze the optimization landscapes of deep learning with wide networks. We highlight the importance of constraints for such networks and show that constraint -- as well as unconstraint -- empirical-risk minimization over such networks…

Machine Learning · Computer Science 2021-01-14 Johannes Lederer

Training neural networks means solving a high-dimensional optimization problem. Normally the goal is to minimize a loss function that depends on what is called the network function, or in other words the function that gives the network…

Machine Learning · Computer Science 2022-11-15 Umberto Michelucci

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
‹ Prev 1 3 4 5 6 7 10 Next ›