English
Related papers

Related papers: Sketchy Empirical Natural Gradient Methods for Dee…

200 papers

We propose a randomized first order optimization method--SEGA (SkEtched GrAdient method)-- which progressively throughout its iterations builds a variance-reduced estimate of the gradient from random linear measurements (sketches) of the…

Optimization and Control · Mathematics 2018-10-19 Filip Hanzely , Konstantin Mishchenko , Peter Richtarik

Natural gradient descent (NGD) is a powerful optimization technique for machine learning, but the computational complexity of the inverse Fisher information matrix limits its application in training deep neural networks. To overcome this…

Machine Learning · Computer Science 2024-12-11 Weihua Liu , Said Boumaraf , Jianwu Li , Chaochao Lin , Xiabi Liu , Lijuan Niu , Naoufel Werghi

Large-scale distributed training of deep neural networks results in models with worse generalization performance as a result of the increase in the effective mini-batch size. Previous approaches attempt to address this problem by varying…

Machine Learning · Computer Science 2020-02-17 Kazuki Osawa , Yohei Tsuji , Yuichiro Ueno , Akira Naruse , Chuan-Sheng Foo , Rio Yokota

Uncertainty estimation in large deep-learning models is a computationally challenging task, where it is difficult to form even a Gaussian approximation to the posterior distribution. In such situations, existing methods usually resort to a…

Machine Learning · Computer Science 2019-01-15 Aaron Mishkin , Frederik Kunstner , Didrik Nielsen , Mark Schmidt , Mohammad Emtiyaz Khan

Graph Neural Networks (GNNs) are widely applied to graph learning problems such as node classification. When scaling up the underlying graphs of GNNs to a larger size, we are forced to either train on the complete graph and keep the full…

Machine Learning · Computer Science 2024-06-25 Mucong Ding , Tahseen Rabbani , Bang An , Evan Z Wang , Furong Huang

Sketching is one of the most fundamental tools in large-scale machine learning. It enables runtime and memory saving via randomly compressing the original large problem into lower dimensions. In this paper, we propose a novel sketching…

Machine Learning · Computer Science 2023-06-08 Zhao Song , Yitan Wang , Zheng Yu , Lichen Zhang

We introduce SketchGNN, a convolutional graph neural network for semantic segmentation and labeling of freehand vector sketches. We treat an input stroke-based sketch as a graph, with nodes representing the sampled points along input…

Computer Vision and Pattern Recognition · Computer Science 2021-03-26 Lumin Yang , Jiajie Zhuang , Hongbo Fu , Xiangzhi Wei , Kun Zhou , Youyi Zheng

Deep learning has made profound impacts in the domains of data mining and AI, distinguished by the groundbreaking achievements in numerous real-world applications and the innovative algorithm design philosophy. However, it suffers from the…

Machine Learning · Computer Science 2024-09-24 Di Wang , Shao-Bo Lin , Deyu Meng , Feilong Cao

Subsampled natural gradient descent (SNG) has been used to enable high-precision scientific machine learning, but standard analyses based on stochastic preconditioning fail to provide insight into realistic small-sample settings. We…

Machine Learning · Computer Science 2026-02-06 Gil Goldshlager , Jiang Hu , Lin Lin

This work proposes a time-efficient Natural Gradient Descent method, called TENGraD, with linear convergence guarantees. Computing the inverse of the neural network's Fisher information matrix is expensive in NGD because the Fisher matrix…

Machine Learning · Computer Science 2022-03-04 Saeed Soori , Bugra Can , Baourun Mu , Mert Gürbüzbalaban , Maryam Mehri Dehnavi

Partial differential equations (PDEs) are instrumental for modeling dynamical systems in science and engineering. The advent of neural networks has initiated a significant shift in tackling these complexities though challenges in accuracy…

Machine Learning · Computer Science 2024-06-07 Zhuo Chen , Jacob McCarran , Esteban Vizcaino , Marin Soljačić , Di Luo

Distributed training is an effective way to accelerate the training process of large-scale deep learning models. However, the parameter exchange and synchronization of distributed stochastic gradient descent introduce a large amount of…

Distributed, Parallel, and Cluster Computing · Computer Science 2021-08-16 LingFei Dai , Boyu Diao , Chao Li , Yongjun Xu

We present practical Levenberg-Marquardt variants of Gauss-Newton and natural gradient methods for solving non-convex optimization problems that arise in training deep neural networks involving enormous numbers of variables and huge data…

Machine Learning · Computer Science 2019-06-07 Yi Ren , Donald Goldfarb

Deep learning, a rebranding of deep neural network research works, has achieved a remarkable success in recent years. With multiple hidden layers, deep learning models aim at computing the hierarchical feature representations of the…

Neural and Evolutionary Computing · Computer Science 2018-06-06 Jiawei Zhang , Limeng Cui , Fisher B. Gouza

Sketching and stochastic gradient methods are arguably the most common techniques to derive efficient large scale learning algorithms. In this paper, we investigate their application in the context of nonparametric statistical learning.…

Machine Learning · Statistics 2019-01-25 Luigi Carratino , Alessandro Rudi , Lorenzo Rosasco

Deep Neural Network (DNN) acoustic models often use discriminative sequence training that optimises an objective function that better approximates the word error rate (WER) than frame-based training. Sequence training is normally…

Computation and Language · Computer Science 2018-04-09 Adnan Haider , Philip C. Woodland

Stochastic Gradient Descent (SGD), a widely used optimization algorithm in deep learning, is often limited to converging to local optima due to the non-convex nature of the problem. Leveraging these local optima to improve model performance…

Machine Learning · Computer Science 2023-09-22 Hao Chen , Yusen Wu , Phuong Nguyen , Chao Liu , Yelena Yesha

Leveraging the kernel trick in both the input and output spaces, surrogate kernel methods are a flexible and theoretically grounded solution to structured output prediction. If they provide state-of-the-art performance on complex data sets…

Machine Learning · Statistics 2024-05-07 Tamim El Ahmad , Luc Brogat-Motte , Pierre Laforgue , Florence d'Alché-Buc

In this paper, we develop a novel procedure for low-rank tensor regression, namely \emph{\underline{I}mportance \underline{S}ketching \underline{L}ow-rank \underline{E}stimation for \underline{T}ensors} (ISLET). The central idea behind…

Machine Learning · Statistics 2020-05-11 Anru Zhang , Yuetian Luo , Garvesh Raskutti , Ming Yuan

Natural Gradient Descent, a second-degree optimization method motivated by the information geometry, makes use of the Fisher Information Matrix instead of the Hessian which is typically used. However, in many cases, the Fisher Information…

Machine Learning · Computer Science 2023-03-10 Rajesh Shrestha
‹ Prev 1 2 3 10 Next ›