English
Related papers

Related papers: Orthogonal Weight Normalization: Solution to Optim…

200 papers

A deep neural network of multiple nonlinear layers forms a large function space, which can easily lead to overfitting when it encounters small-sample data. To mitigate overfitting in small-sample classification, learning more discriminative…

Computer Vision and Pattern Recognition · Computer Science 2020-07-15 Xiaoxu Li , Dongliang Chang , Zhanyu Ma , Zheng-Hua Tan , Jing-Hao Xue , Jie Cao , Jingyi Yu , Jun Guo

The inductive bias of a neural network is largely determined by the architecture and the training algorithm. To achieve good generalization, how to effectively train a neural network is of great importance. We propose a novel orthogonal…

Machine Learning · Computer Science 2021-06-08 Weiyang Liu , Rongmei Lin , Zhen Liu , James M. Rehg , Liam Paull , Li Xiong , Le Song , Adrian Weller

Training recurrent neural networks (RNNs) is a hard problem due to degeneracies in the optimization landscape, a problem also known as vanishing/exploding gradients. Short of designing new RNN architectures, previous methods for dealing…

Neural and Evolutionary Computing · Computer Science 2020-02-11 A. Emin Orhan , Xaq Pitkow

As a randomized learner model, SCNs are remarkable that the random weights and biases are assigned employing a supervisory mechanism to ensure universal approximation and fast learning. However, the randomness makes SCNs more likely to…

Machine Learning · Computer Science 2022-05-27 Wei Dai , Chuanfeng Ning , Shiyu Pei , Song Zhu , Xuesong Wang

The problem of learning long-term dependencies in sequences using Recurrent Neural Networks (RNNs) is still a major challenge. Recent methods have been suggested to solve this problem by constraining the transition matrix to be unitary…

Machine Learning · Computer Science 2017-06-14 Zakaria Mhammedi , Andrew Hellicar , Ashfaqur Rahman , James Bailey

It is well known that it is challenging to train deep neural networks and recurrent neural networks for tasks that exhibit long term dependencies. The vanishing or exploding gradient problem is a well known issue associated with these…

Machine Learning · Computer Science 2017-10-13 Eugene Vorontsov , Chiheb Trabelsi , Samuel Kadoury , Chris Pal

Enforcing orthogonality in neural networks is an antidote for gradient vanishing/exploding problems, sensitivity by adversarial perturbation, and bounding generalization errors. However, many previous approaches are heuristic, and the…

Machine Learning · Computer Science 2021-06-18 Jiahao Su , Wonmin Byeon , Furong Huang

Orthogonality constraints naturally appear in many machine learning problems, from principal component analysis to robust neural network training. They are usually solved using Riemannian optimization algorithms, which minimize the…

Machine Learning · Statistics 2025-08-08 Pierre Ablin , Simon Vary , Bin Gao , P. -A. Absil

Orthogonal neural networks have recently been introduced as a new type of neural networks imposing orthogonality on the weight matrices. They could achieve higher accuracy and avoid evanescent or explosive gradients for deep architectures.…

Quantum Physics · Physics 2022-12-26 Iordanis Kerenidis , Jonas Landman , Natansh Mathur

Initialising the synaptic weights of artificial neural networks (ANNs) with orthogonal matrices is known to alleviate vanishing and exploding gradient problems. A major objection against such initialisation schemes is that they are deemed…

Neural and Evolutionary Computing · Computer Science 2023-03-23 Nikolay Manchev , Michael Spratling

Retrieval systems rely on representations learned by increasingly powerful models. However, due to the high training cost and inconsistencies in learned representations, there is significant interest in facilitating communication between…

Machine Learning · Computer Science 2026-05-20 Simone Ricci , Niccolò Biondi , Federico Pernici , Ioannis Patras , Alberto Del Bimbo

Stable and efficient training of ReLU networks with large depth is highly sensitive to weight initialization. Improper initialization can cause permanent neuron inactivation dying ReLU and exacerbate gradient instability as network depth…

Machine Learning · Computer Science 2025-09-03 Hyungu Lee , Taehyeong Kim , Hayoung Choi

Orthogonal finetuning (OFT) offers highly parameter-efficient adaptation while preventing catastrophic forgetting, but its high runtime and memory demands limit practical deployment. We identify the core computational bottleneck in OFT as…

Machine Learning · Computer Science 2025-10-16 Zeju Qiu , Weiyang Liu , Adrian Weller , Bernhard Schölkopf

Recently, orthogonal recurrent neural networks (RNNs) have emerged as state-of-the-art models for learning long-term dependencies. This class of models mitigates the exploding and vanishing gradients problem by design. In this work, we…

Machine Learning · Computer Science 2021-02-22 Omri Azencot , N. Benjamin Erichson , Mirela Ben-Chen , Michael W. Mahoney

In this work, we propose a new training method for finding minimum weight norm solutions in over-parameterized neural networks (NNs). This method seeks to improve training speed and generalization performance by framing NN training as a…

Machine Learning · Statistics 2018-06-22 Yamini Bansal , Madhu Advani , David D Cox , Andrew M Saxe

In this paper we approach the problem of unique and stable identifiability of generic deep artificial neural networks with pyramidal shape and smooth activation functions from a finite number of input-output samples. More specifically we…

Machine Learning · Computer Science 2021-01-19 Christian Fiedler , Massimo Fornasier , Timo Klock , Michael Rauchensteiner

In this article, we introduce a novel normalization technique for neural network weight matrices, which we term weight conditioning. This approach aims to narrow the gap between the smallest and largest singular values of the weight…

Computer Vision and Pattern Recognition · Computer Science 2026-03-16 Hemanth Saratchandran , Thomas X. Wang , Simon Lucey

Recently mean field theory has been successfully used to analyze properties of wide, random neural networks. It gave rise to a prescriptive theory for initializing feed-forward neural networks with orthogonal weights, which ensures that…

Machine Learning · Statistics 2019-06-05 Piotr A. Sokol , Il Memming Park

We consider the problem of minimizing a non-convex function over a smooth manifold $\mathcal{M}$. We propose a novel algorithm, the Orthogonal Directions Constrained Gradient Method (ODCGM) which only requires computing a projection onto a…

Optimization and Control · Mathematics 2023-03-17 Sholom Schechtman , Daniil Tiapkin , Michael Muehlebach , Eric Moulines

Imposing orthogonality on the layers of neural networks is known to facilitate the learning by limiting the exploding/vanishing of the gradient; decorrelate the features; improve the robustness. This paper studies the theoretical properties…

Statistics Theory · Mathematics 2023-01-16 El Mehdi Achour , François Malgouyres , Franck Mamalet