English
Related papers

Related papers: Orthogonal Weight Normalization: Solution to Optim…

200 papers

In this paper, we investigate the empirical impact of orthogonality regularization (OR) in deep learning, either solo or collaboratively. Recent works on OR showed some promising results on the accuracy. In our ablation study, however, we…

Computer Vision and Pattern Recognition · Computer Science 2020-01-20 Ziming Zhang , Wenchi Ma , Yuanwei Wu , Guanghui Wang

Deep neural network is difficult to train and this predicament becomes worse as the depth increases. The essence of this problem exists in the magnitude of backpropagated errors that will result in gradient vanishing or exploding…

Computer Vision and Pattern Recognition · Computer Science 2017-04-11 Di Xie , Jiang Xiong , Shiliang Pu

Deep neural network (DNN) generally takes thousands of iterations to optimize via gradient descent and thus has a slow convergence. In addition, softmax, as a decision layer, may ignore the distribution information of the data during…

Machine Learning · Computer Science 2021-06-16 Rui Zhang , Ziheng Jiao , Hongyuan Zhang , Xuelong Li

The single-layer feedforward neural network with random weights is a recurring motif in the neural networks literature. The advantage of these networks is their simplified training, which reduces to solving a ridge-regression problem. A…

Machine Learning · Computer Science 2025-02-25 M. Andrecut

Machine learning surrogate models have emerged as a promising approach for accelerating multiscale materials simulations while preserving predictive fidelity. Among them, the Orientation-aware Interaction-based Deep Material Network (ODMN)…

Computational Engineering, Finance, and Science · Computer Science 2026-04-09 Ting-Ju Wei , Tung-Huan Su , Chuin-Shan Chen

Orthogonal parameterization is a compelling solution to the vanishing gradient problem (VGP) in recurrent neural networks (RNNs). With orthogonal parameters and non-saturated activation functions, gradients in such models are constrained to…

Machine Learning · Computer Science 2023-04-25 Khoi Minh Nguyen-Duy , Quang Pham , Binh T. Nguyen

Classical neural network approximation results take the form: for every function $f$ and every error tolerance $\epsilon > 0$, one constructs a neural network whose architecture and weights depend on $\epsilon$. This paper introduces a…

Neural and Evolutionary Computing · Computer Science 2025-11-20 Clemens Hutter , Valentin Abadie , Helmut Bölcskei

Muon improves neural-network training by orthogonalizing matrix-valued updates, but it leaves each layer's update magnitude controlled mostly by a global learning rate. We introduce OrScale, a trust-ratio extension of Muon built on a simple…

Machine Learning · Computer Science 2026-05-11 Yuxuan Lou , Yang You

Reinforcement learning (RL) has made significant advancements, achieving superhuman performance in various tasks. However, RL agents often operate under the assumption of environmental stationarity, which poses a great challenge to learning…

Machine Learning · Computer Science 2025-11-18 Guoqing Ma , Yuhan Zhang , Yuming Dai , Guangfu Hao , Yang Chen , Shan Yu

We propose the framework of dual convexified convolutional neural networks (DCCNNs). In this framework, we first introduce a primal learning problem motivated by convexified convolutional neural networks (CCNNs), and then construct the dual…

Machine Learning · Computer Science 2024-09-17 Site Bai , Chuyang Ke , Jean Honorio

Deep learning algorithms have achieved excellent performance lately in a wide range of fields (e.g., computer version). However, a severe challenge faced by deep learning is the high dependency on hyper-parameters. The algorithm results may…

Machine Learning · Computer Science 2020-03-02 Xiang Zhang , Xiaocong Chen , Lina Yao , Chang Ge , Manqing Dong

Weight-sharing is ubiquitous in deep learning. Motivated by this, we propose a "weight-sharing regularization" penalty on the weights $w \in \mathbb{R}^d$ of a neural network, defined as $\mathcal{R}(w) = \frac{1}{d - 1}\sum_{i > j}^d |w_i…

Machine Learning · Computer Science 2024-03-12 Mehran Shakerinava , Motahareh Sohrabi , Siamak Ravanbakhsh , Simon Lacoste-Julien

We consider a class of structured, nonconvex, nonsmooth optimization problems under orthogonality constraints, where the objectives combine a smooth function, a nonsmooth concave function, and a nonsmooth weakly convex function. This class…

Optimization and Control · Mathematics 2025-01-14 Ganzhao Yuan

This paper introduces a novel algorithmic framework for a deep neural network (DNN), which in a mathematically rigorous manner, allows us to incorporate history (or memory) into the network -- it ensures all layers are connected to one…

Optimization and Control · Mathematics 2020-04-03 Harbir Antil , Ratna Khatri , Rainald Löhner , Deepanshu Verma

Multimodal imaging has transformed neuroscience research. While it presents unprecedented opportunities, it also imposes serious challenges. Particularly, it is difficult to combine the merits of the interpretability attributed to a simple…

Methodology · Statistics 2021-11-25 Xiaowu Dai , Lexin Li

Deep learning methods achieve great success recently on many computer vision problems, with image classification and object detection as the prominent examples. In spite of these practical successes, optimization of deep networks remains an…

Computer Vision and Pattern Recognition · Computer Science 2017-03-21 Kui Jia

In deformable registration, the geometric framework - large deformation diffeomorphic metric mapping or LDDMM, in short - has inspired numerous techniques for comparing, deforming, averaging and analyzing shapes or images. Grounded in…

Artificial Intelligence · Computer Science 2022-05-11 Boulbaba Ben Amor , Sylvain Arguillère , Ling Shao

Random Matrix Theory (RMT) is applied to analyze the weight matrices of Deep Neural Networks (DNNs), including both production quality, pre-trained models such as AlexNet and Inception, and smaller models trained from scratch, such as…

Machine Learning · Computer Science 2019-01-25 Charles H. Martin , Michael W. Mahoney

We explore in detail a method to solve ordinary differential equations using feedforward neural networks. We prove a specific loss function, which does not require knowledge of the exact solution, to be a suitable standard metric to…

Computational Physics · Physics 2020-06-02 Liam L. H. Lau , Denis Werth

Strictly enforcing orthonormality constraints on parameter matrices has been shown advantageous in deep learning. This amounts to Riemannian optimization on the Stiefel manifold, which, however, is computationally expensive. To address this…

Machine Learning · Computer Science 2020-02-05 Jun Li , Li Fuxin , Sinisa Todorovic
‹ Prev 1 3 4 5 6 7 10 Next ›