中文
相关论文

相关论文: Training Scale-Invariant Neural Networks on the Sp…

200 篇论文

Normalization Layers (NLs) are widely used in modern deep-learning architectures. Despite their apparent simplicity, their effect on optimization is not yet fully understood. This paper introduces a spherical framework to study the…

机器学习 · 计算机科学 2022-05-20 Simon Roburin , Yann de Mont-Marin , Andrei Bursuc , Renaud Marlet , Patrick Pérez , Mathieu Aubry

Inspired by two basic mechanisms in animal visual systems, we introduce a feature transform technique that imposes invariance properties in the training of deep neural networks. The resulting algorithm requires less parameter tuning, trains…

计算机视觉与模式识别 · 计算机科学 2021-12-10 Chengxi Ye , Xiong Zhou , Tristan McKinney , Yanfeng Liu , Qinggang Zhou , Fedor Zhdanov

Scaling limits, such as infinite-width limits, serve as promising theoretical tools to study large-scale models. However, it is widely believed that existing infinite-width theory does not faithfully explain the behavior of practical…

机器学习 · 计算机科学 2025-10-28 Moritz Haas , Sebastian Bordt , Ulrike von Luxburg , Leena Chennuru Vankadara

Analyzing scalar and vector fields on the sphere, such as temperature or wind speed and direction on Earth, is a difficult task. Models should respect both the rotational symmetries of the sphere and the inherent symmetries of the vector…

机器学习 · 计算机科学 2026-04-01 Francesco Ballerin , Nello Blaser , Erlend Grong

Training neural networks is an optimization problem, and finding a decent set of parameters through gradient descent can be a difficult task. A host of techniques has been developed to aid this process before and during the training phase.…

机器学习 · 计算机科学 2020-08-19 Divya Gaur , Joachim Folz , Andreas Dengel

Recent studies have shown that high disparities in effective learning rates (ELRs) across layers in deep neural networks can negatively affect trainability. We formalize how these disparities evolve over time by modeling weight dynamics…

机器学习 · 计算机科学 2024-05-27 Christian H. X. Ali Mehmeti-Göpel , Michael Wand

When optimizing over-parameterized models, such as deep neural networks, a large set of parameters can achieve zero training error. In such cases, the choice of the optimization algorithm and its respective hyper-parameters introduces…

机器学习 · 计算机科学 2019-12-06 Gauthier Gidel , Francis Bach , Simon Lacoste-Julien

In recent years, a variety of normalization methods have been proposed to help train neural networks, such as batch normalization (BN), layer normalization (LN), weight normalization (WN), group normalization (GN), etc. However,…

机器学习 · 计算机科学 2020-06-17 Jiacheng Sun , Xiangyong Cao , Hanwen Liang , Weiran Huang , Zewei Chen , Zhenguo Li

We consider the problem of learning an unknown function $f_{\star}$ on the $d$-dimensional sphere with respect to the square loss, given i.i.d. samples $\{(y_i,{\boldsymbol x}_i)\}_{i\le n}$ where ${\boldsymbol x}_i$ is a feature vector…

统计理论 · 数学 2020-02-18 Behrooz Ghorbani , Song Mei , Theodor Misiakiewicz , Andrea Montanari

Understanding the dynamics of neural networks in different width regimes is crucial for improving their training and performance. We present an exact solution for the learning dynamics of a one-hidden-layer linear network, with…

机器学习 · 计算机科学 2025-02-24 Yizhou Xu , Liu Ziyin

Recent works (e.g., (Li and Arora, 2020)) suggest that the use of popular normalization schemes (including Batch Normalization) in today's deep learning can move it far from a traditional optimization viewpoint, e.g., use of exponentially…

机器学习 · 计算机科学 2020-10-07 Zhiyuan Li , Kaifeng Lyu , Sanjeev Arora

Neural networks trained via gradient descent with random initialization and without any regularization enjoy good generalization performance in practice despite being highly overparametrized. A promising direction to explain this phenomenon…

机器学习 · 计算机科学 2022-05-17 Hancheng Min , Salma Tarmoun , Rene Vidal , Enrique Mallada

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…

机器学习 · 计算机科学 2015-03-03 Sergey Ioffe , Christian Szegedy

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…

机器学习 · 计算机科学 2021-12-21 Karl Hajjar , Lénaïc Chizat , Christophe Giraud

We study the optimization landscape and the stability properties of training problems with squared loss for neural networks and general nonlinear conic approximation schemes. It is demonstrated that, if a nonlinear conic approximation…

最优化与控制 · 数学 2021-12-03 Constantin Christof

The successful training of deep neural networks requires addressing challenges such as overfitting, numerical instabilities leading to divergence, and increasing variance in the residual stream. A common solution is to apply regularization…

Existing large-dimensional theory for spectral algorithms resolves either the optimally tuned point or the interpolation limit, but leaves the under-regularized regime unexplored. We study the learning curve and benign overfitting of…

机器学习 · 统计学 2026-04-28 Weihao Lu , Qian Lin , Yingcun Xia , Dongming Huang

Training deep neural networks is a very demanding task, especially challenging is how to adapt architectures to improve the performance of trained models. We can find that sometimes, shallow networks generalize better than deep networks,…

机器学习 · 计算机科学 2022-08-03 David Peer , Bart Keulen , Sebastian Stabinger , Justus Piater , Antonio Rodríguez-Sánchez

A common challenge in regression is that for many problems, the degrees of freedom required for a high-quality solution also allows for overfitting. Regularization is a class of strategies that seek to restrict the range of possible…

机器学习 · 计算机科学 2022-11-15 Colin Ponce , Ruipeng Li , Christina Mao , Panayot Vassilevski

Sparse neural networks are highly desirable in deep learning in reducing its complexity. The goal of this paper is to study how choices of regularization parameters influence the sparsity level of learned neural networks. We first derive…

机器学习 · 计算机科学 2024-08-07 Lixin Shen , Rui Wang , Yuesheng Xu , Mingsong Yan
‹ 上一页 1 2 3 10 下一页 ›