中文
相关论文

相关论文: Convergence Analysis of Natural Gradient Descent f…

200 篇论文

3D Gaussian Splatting (3DGS) has emerged as a mainstream solution for novel view synthesis and 3D reconstruction. By explicitly encoding a 3D scene using a collection of Gaussian kernels, 3DGS achieves high-quality rendering with superior…

计算机视觉与模式识别 · 计算机科学 2025-01-28 Lei Lan , Tianjia Shao , Zixuan Lu , Yu Zhang , Chenfanfu Jiang , Yin Yang

We study a fully decentralized federated learning algorithm, which is a novel gradient descent algorithm executed on a communication-based network. For convenience, we refer to it as a network gradient descent (NGD) method. In the NGD…

机器学习 · 计算机科学 2022-05-18 Shuyuan Wu , Danyang Huang , Hansheng Wang

Physics-informed neural networks (PINNs) offer a mesh-free framework for solving partial differential equations (PDEs), yet training often suffers from gradient pathologies, spectral bias, and poor convergence, especially for problems with…

机器学习 · 计算机科学 2026-05-20 Jianan Yang , Yiran Wang , Shuai Li , Fujun Cao , Xuefei Yan , Junmin Liu

Partial differential equations (PDEs) provide a mathematical foundation for simulating and understanding intricate behaviors in both physical sciences and engineering. With the growing capabilities of deep learning, data$-$driven approaches…

机器学习 · 计算机科学 2025-10-14 Narayan S Iyer , Bivas Bhaumik , Ram S Iyer , Satyasaran Changdar

We give a simple proof for the global convergence of gradient descent in training deep ReLU networks with the standard square loss, and show some of its improvements over the state-of-the-art. In particular, while prior works require all…

机器学习 · 计算机科学 2021-06-14 Quynh Nguyen

Gradient clipping is commonly used in training deep neural networks partly due to its practicability in relieving the exploding gradient problem. Recently, \citet{zhang2019gradient} show that clipped (stochastic) Gradient Descent (GD)…

机器学习 · 计算机科学 2020-10-30 Bohang Zhang , Jikai Jin , Cong Fang , Liwei Wang

Although deep learning has shown its powerful performance in many applications, the mathematical principles behind neural networks are still mysterious. In this paper, we consider the problem of learning a one-hidden-layer neural network…

机器学习 · 计算机科学 2019-07-17 Shuhao Xia , Yuanming Shi

Stochastic Gradient Descent (SGD) methods are prominent for training machine learning and deep learning models. The performance of these techniques depends on their hyperparameter tuning over time and varies for different models and…

机器学习 · 统计学 2019-08-22 Tomer Lancewicki , Selcuk Kopru

This work analyzes the solution trajectory of gradient-based algorithms via a novel basis function decomposition. We show that, although solution trajectories of gradient-based algorithms may vary depending on the learning task, they behave…

机器学习 · 计算机科学 2022-10-05 Jianhao Ma , Lingjun Guo , Salar Fattahi

Modern deep learning techniques focus on extracting intricate information from data to achieve accurate predictions. However, the training datasets may be crowdsourced and include sensitive information, such as personal contact details,…

机器学习 · 统计学 2026-02-10 Zhongjie Shi , Puyu Wang , Chenyang Zhang , Yuan Cao

The theory of training deep networks has become a central question of modern machine learning and has inspired many practical advancements. In particular, the gradient descent (GD) optimization algorithm has been extensively studied in…

最优化与控制 · 数学 2025-10-29 Alexandru Crăciun , Debarghya Ghoshdastidar

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…

机器学习 · 统计学 2018-03-23 Hartmut Maennel , Olivier Bousquet , Sylvain Gelly

In this paper, we present some theoretical work to explain why simple gradient descent methods are so successful in solving non-convex optimization problems in learning large-scale neural networks (NN). After introducing a mathematical tool…

机器学习 · 计算机科学 2023-05-01 Hui Jiang

We study statistical inverse learning in the context of nonlinear inverse problems under random design. Specifically, we address a class of nonlinear problems by employing gradient descent (GD) and stochastic gradient descent (SGD) with…

机器学习 · 统计学 2024-12-24 Abhishake , Nicole Mücke , Tapio Helin

Communication has been seen as a significant bottleneck in industrial applications over large-scale networks. To alleviate the communication burden, sign-based optimization algorithms have gained popularity recently in both industrial and…

最优化与控制 · 数学 2021-09-07 Xiuxian Li , Kuo-Yi Lin , Li Li , Yiguang Hong , Jie Chen

We propose an algorithm for the adaptation of the learning rate for stochastic gradient descent (SGD) that avoids the need for validation set use. The idea for the adaptiveness comes from the technique of extrapolation: to get an estimate…

机器学习 · 统计学 2020-08-28 Antti Koskela , Antti Honkela

As a second-order method, the Natural Gradient Descent (NGD) has the ability to accelerate training of neural networks. However, due to the prohibitive computational and memory costs of computing and inverting the Fisher Information Matrix…

Recent works have empirically analyzed in-context learning and shown that transformers trained on synthetic linear regression tasks can learn to implement ridge regression, which is the Bayes-optimal predictor, given sufficient capacity…

机器学习 · 计算机科学 2023-07-10 Arvind Mahankali , Tatsunori B. Hashimoto , Tengyu Ma

Despite recent theoretical progress on the non-convex optimization of two-layer neural networks, it is still an open question whether gradient descent on neural networks without unnatural modifications can achieve better sample complexity…

机器学习 · 计算机科学 2023-10-10 Arvind Mahankali , Jeff Z. Haochen , Kefan Dong , Margalit Glasgow , Tengyu Ma

Gradient descent (GD) type optimization schemes are the standard methods to train artificial neural networks (ANNs) with rectified linear unit (ReLU) activation. Such schemes can be considered as discretizations of gradient flows (GFs)…

机器学习 · 计算机科学 2022-09-27 Arnulf Jentzen , Adrian Riekert