English
Related papers

Related papers: A Dual-Dimer Method for Training Physics-Constrain…

200 papers

In this paper, we unroll the dynamics of the dual ascent (DA) algorithm in two coupled graph neural networks (GNNs) to solve constrained optimization problems. The two networks interact with each other at the layer level to find a saddle…

Machine Learning · Computer Science 2026-02-03 Samar Hadou , Alejandro Ribeiro

Training neural networks is a challenging non-convex optimization problem, and backpropagation or gradient descent can get stuck in spurious local optima. We propose a novel algorithm based on tensor decomposition for guaranteed training of…

Machine Learning · Computer Science 2016-01-13 Majid Janzamin , Hanie Sedghi , Anima Anandkumar

Deep neural networks (DNNs) are becoming increasingly deeper, wider, and non-linear due to the growing demands on prediction accuracy and analysis quality. When training a DNN model, the intermediate activation data must be saved in the…

Distributed, Parallel, and Cluster Computing · Computer Science 2020-11-24 Sian Jin , Guanpeng Li , Shuaiwen Leon Song , Dingwen Tao

With more and more data being collected, data-driven modeling methods have been gaining in popularity in recent years. While physically sound, classical gray-box models are often cumbersome to identify and scale, and their accuracy might be…

Machine Learning · Computer Science 2023-04-05 Loris Di Natale , Bratislav Svetozarevic , Philipp Heer , Colin Neil Jones

Learning in Deep Neural Networks (DNN) takes place by minimizing a non-convex high-dimensional loss function, typically by a stochastic gradient descent (SGD) strategy. The learning process is observed to be able to find good minimizers…

Machine Learning · Computer Science 2020-03-12 Carlo Baldassi , Fabrizio Pittorino , Riccardo Zecchina

Supervised training of deep neural nets typically relies on minimizing cross-entropy. However, in many domains, we are interested in performing well on metrics specific to the application. In this paper we propose a direct loss minimization…

Machine Learning · Computer Science 2016-06-03 Yang Song , Alexander G. Schwing , Richard S. Zemel , Raquel Urtasun

Compared to classical deep neural networks its binarized versions can be useful for applications on resource-limited devices due to their reduction in memory consumption and computational demands. In this work we study deep neural networks…

Optimization and Control · Mathematics 2021-10-26 Jannis Kurtz , Bubacarr Bah

Physics-informed Neural Networks (PINNs) often have, in their loss functions, terms based on physical equations and derivatives. In order to evaluate these terms, the output solution is sampled using a distribution of collocation points.…

Machine Learning · Computer Science 2022-11-23 Marcus Münzer , Chris Bard

Adversarial neural networks solve many important problems in data science, but are notoriously difficult to train. These difficulties come from the fact that optimal weights for adversarial nets correspond to saddle points, and not…

Machine Learning · Computer Science 2018-02-12 Abhay Yadav , Sohil Shah , Zheng Xu , David Jacobs , Tom Goldstein

Limited by the operation and measurement conditions, numerical simulation is often the only feasible approach for studying plasma behavior and mechanisms. Although artificial intelligence methods, especially physics-informed neural network…

Computational Physics · Physics 2025-01-28 Yifan Wang , Linlin Zhong

Binary Neural Networks (BNNs) are an extremely promising method to reduce deep neural networks' complexity and power consumption massively. Binarization techniques, however, suffer from ineligible performance degradation compared to their…

Machine Learning · Computer Science 2022-04-06 Tal Rozen , Moshe Kimhi , Brian Chmiel , Avi Mendelson , Chaim Baskin

In this work, we propose a network which can utilize computational cheap low-fidelity data together with limited high-fidelity data to train surrogate models, where the multi-fidelity data are generated from multiple underlying models. The…

Computational Physics · Physics 2020-10-06 Yating Wang , Guang Lin

The state-of-art DNN structures involve high computation and great demand for memory storage which pose intensive challenge on DNN framework resources. To mitigate the challenges, weight pruning techniques has been studied. However, high…

Machine Learning · Computer Science 2019-05-03 Xiaolong Ma , Geng Yuan , Sheng Lin , Zhengang Li , Hao Sun , Yanzhi Wang

This paper works on Binary Neural Networks (BNNs), a promising avenue for efficient deep learning, offering significant reductions in computational overhead and memory footprint to full precision networks. However, the challenge of…

Machine Learning · Computer Science 2024-10-02 Federico Fontana , Romeo Lanzino , Anxhelo Diko , Gian Luca Foresti , Luigi Cinque

DNNs deployed on analog processing in memory (PIM) architectures are subject to fabrication-time variability. We developed a new joint variability- and quantization-aware DNN training algorithm for highly quantized analog PIM-based models…

Machine Learning · Computer Science 2021-11-15 Zihao Deng , Michael Orshansky

Low-precision deep neural network (DNN) training has gained tremendous attention as reducing precision is one of the most effective knobs for boosting DNNs' training time/energy efficiency. In this paper, we attempt to explore low-precision…

Machine Learning · Computer Science 2025-01-07 Yonggan Fu , Han Guo , Meng Li , Xin Yang , Yining Ding , Vikas Chandra , Yingyan Celine Lin

With several advantages and as an alternative to predict physics field, machine learning methods can be classified into two distinct types: data-driven relying on training data and physics-driven using physics law. Choosing heat conduction…

Computational Physics · Physics 2020-05-19 Hao Ma , Xiangyu Hu , Yuxuan Zhang , Nils Thuerey , Oskar J. Haidn

In this paper, we consider approximating the parameter-to-solution maps of parametric partial differential equations (PPDEs) using deep neural networks (DNNs). We propose an efficient approach combining reduced collocation methods (RCMs)…

Numerical Analysis · Mathematics 2025-08-18 Guanhang Lei , Zhen Lei , Lei Shi , Chenyu Zeng

Deep Convolutional Neural Networks (CNN) have been successfully applied to many real-life problems. However, the huge memory cost of deep CNN models poses a great challenge of deploying them on memory-constrained devices (e.g., mobile…

Computer Vision and Pattern Recognition · Computer Science 2020-10-07 Weichao Lan , Liang Lan

Lightweight design, as a key approach to mitigate disparity between computational requirements of deep learning models and hardware performance, plays a pivotal role in advancing application of deep learning technologies on mobile and…

Computer Vision and Pattern Recognition · Computer Science 2024-12-24 Hanhua Long , Wenbin Bi , Jian Sun