English
Related papers

Related papers: NG+ : A Multi-Step Matrix-Product Natural Gradient…

200 papers

Generative adversarial imitation learning (GAIL) is a popular inverse reinforcement learning approach for jointly optimizing policy and reward from expert trajectories. A primary question about GAIL is whether applying a certain policy…

Machine Learning · Computer Science 2020-06-26 Ziwei Guan , Tengyu Xu , Yingbin Liang

Training a very deep neural network is a challenging task, as the deeper a neural network is, the more non-linear it is. We compare the performances of various preconditioned Langevin algorithms with their non-Langevin counterparts for the…

Machine Learning · Computer Science 2023-01-02 Pierre Bras

This paper establishes a mathematical foundation for the Adam optimizer, elucidating its connection to natural gradient descent through Riemannian and information geometry. We provide an accessible and detailed analysis of the diagonal…

Machine Learning · Computer Science 2024-09-05 Dongseong Hwang

The generalized Gauss-Newton (GGN) approximation is often used to make practical Bayesian deep learning approaches scalable by replacing a second order derivative with a product of first order derivatives. In this paper we argue that the…

Machine Learning · Statistics 2021-02-26 Alexander Immer , Maciej Korzepa , Matthias Bauer

How to train deep neural networks (DNNs) to generalize well is a central concern in deep learning, especially for severely overparameterized networks nowadays. In this paper, we propose an effective method to improve the model…

Machine Learning · Computer Science 2022-06-28 Yang Zhao , Hao Zhang , Xiuyuan Hu

Second-order optimization methods have the ability to accelerate convergence by modifying the gradient through the curvature matrix. There have been many attempts to use second-order optimization methods for training deep neural networks.…

Machine Learning · Computer Science 2020-11-24 Kai-Xin Gao , Xiao-Lei Liu , Zheng-Hai Huang , Min Wang , Zidong Wang , Dachuan Xu , Fan Yu

In the context of deep learning, many optimization methods use gradient covariance information in order to accelerate the convergence of Stochastic Gradient Descent. In particular, starting with Adagrad, a seemingly endless line of research…

Machine Learning · Computer Science 2020-12-08 Nikolaos Tselepidis , Jonas Kohler , Antonio Orvieto

The potential of neural networks (NN) in engineering is rooted in their capacity to understand intricate patterns and complex systems, leveraging their universal nonlinear approximation capabilities and high expressivity. Meanwhile,…

Computational Engineering, Finance, and Science · Computer Science 2025-01-23 Mohammed Abda , Elsa Piollet , Christopher Blake , Frédérick P. Gosselin

Minimizing loss functions is central to machine-learning training. Although first-order methods dominate practical applications, higher-order techniques such as Newton's method can deliver greater accuracy and faster convergence, yet are…

Machine Learning · Computer Science 2025-11-25 Giuseppe Carrino , Elena Loli Piccolomini , Elisa Riccietti , Theo Mary

Despite impressive performance as evaluated on i.i.d. holdout data, deep neural networks depend heavily on superficial statistics of the training data and are liable to break under distribution shift. For example, subtle changes to the…

Computer Vision and Pattern Recognition · Computer Science 2019-03-18 Haohan Wang , Zexue He , Zachary C. Lipton , Eric P. Xing

Diffusion has shown great success in improving accuracy of unsupervised image retrieval systems by utilizing high-order structures of image manifold. However, existing diffusion methods suffer from three major limitations: 1) they usually…

Computer Vision and Pattern Recognition · Computer Science 2020-06-15 Zhiyong Dou , Haotian Cui , Lin Zhang , Bo Wang

The generalized Gauss-Newton (GGN) optimization method incorporates curvature estimates into its solution steps, and provides a good approximation to the Newton method for large-scale optimization problems. GGN has been found particularly…

Machine Learning · Computer Science 2024-04-24 Adeyemi D. Adeoye , Philipp Christian Petersen , Alberto Bemporad

Estimating the Hessian matrix, especially for neural network training, is a challenging problem due to high dimensionality and cost. In this work, we compare the classical Sherman-Morrison update used in the popular BFGS method…

Machine Learning · Computer Science 2025-12-09 Adrian Przybysz , Mikołaj Kołek , Franciszek Sobota , Jarek Duda

Normalization is known to help the optimization of deep neural networks. Curiously, different architectures require specialized normalization methods. In this paper, we study what normalization is effective for Graph Neural Networks (GNNs).…

Machine Learning · Computer Science 2021-06-14 Tianle Cai , Shengjie Luo , Keyulu Xu , Di He , Tie-Yan Liu , Liwei Wang

The natural gradient descent optimisation technique is an efficient optimising protocol for broad classes of classical and quantum systems that takes the underlying geometry of the parameter manifold into account by means of using either…

Quantum Physics · Physics 2026-04-08 Ankit Gill , Kunal Pal

Recent studies on transfer learning have shown that selectively fine-tuning a subset of layers or customizing different learning rates for each layer can greatly improve robustness to out-of-distribution (OOD) data and retain generalization…

Computer Vision and Pattern Recognition · Computer Science 2023-03-29 Junjiao Tian , Xiaoliang Dai , Chih-Yao Ma , Zecheng He , Yen-Cheng Liu , Zsolt Kira

In this paper, we introduce the G\"uler-type acceleration technique and utilize it to propose three acceleration algorithms: the G\"uler-type accelerated proximal gradient method (GPGM), the G\"uler-type accelerated linearized augmented…

Optimization and Control · Mathematics 2025-11-24 Bin Zhou , Liusheng Hou , Xingju Cai , Hailin Sun

An appealing property of the natural gradient is that it is invariant to arbitrary differentiable reparameterizations of the model. However, this invariance property requires infinitesimal steps and is lost in practical implementations with…

Machine Learning · Computer Science 2018-06-11 Yang Song , Jiaming Song , Stefano Ermon

The incremental aggregated gradient algorithm is popular in network optimization and machine learning research. However, the current convergence results require the objective function to be strongly convex. And the existing convergence…

Optimization and Control · Mathematics 2019-10-14 Tao Sun , Yuejiao Sun , Dongsheng Li , Qing Liao

Spiking neural networks (SNNs) represent a promising approach in machine learning, combining the hierarchical learning capabilities of deep neural networks with the energy efficiency of spike-based computations. Traditional end-to-end…

Neural and Evolutionary Computing · Computer Science 2024-11-12 Ruyin Wan , Qian Zhang , George Em Karniadakis
‹ Prev 1 8 9 10 Next ›