paper-with-me

홈 › Papers

Orthogonium : A Unified, Efficient Library of Orthogonal and 1-Lipschitz Building Blocks

2026-01-20 · Thibaut Boissin, Franck Mamalet, Valentin Lafargue, Mathieu Serrurier arxiv

Orthogonal and 1-Lipschitz neural network layers are essential building blocks in robust deep learning architectures, crucial for certified adversarial robustness, stable generative models, and reliable recurrent networks. Despite significant advancements, existing implementations remain fragmented, limited, and computationally demanding. To address these issues, we introduce Orthogonium , a unified, efficient, and comprehensive PyTorch library providing orthogonal and 1-Lipschitz layers. Orthogonium provides access to standard convolution features-including support for strides, dilation, grouping, and transposed-while maintaining strict mathematical guarantees. Its optimized implementations reduce overhead on large scale benchmarks such as ImageNet. Moreover, rigorous testing within the library has uncovered critical errors in existing implementations, emphasizing the importance of standardized and reliable tools. Orthogonium thus significantly lowers adoption barriers, enabling scalable experimentation and integration across diverse applications requiring orthogonality and robust Lipschitz constraints. Orthogonium is available at https://github.com/deel-ai/orthogonium.

📄 PDF Abstract BibTeX arXiv:2601.13776

Code (0)

등록된 구현이 없습니다.

Tasks

Adversarial Robustness

Similar Papers 제목 키워드 기반

An Adaptive Orthogonal Convolution Scheme for Efficient and Flexible CNN Architectures

2025-01-14 · Thibaut Boissin, Franck Mamalet, Thomas Fel, Agustin Martin Picard 외

Orthogonal convolutional layers are the workhorse of multiple areas in machine learning, such as adversarial robustness, normalizing flows, GANs, and Lipschitzconstrained models. Their ability to preserve norms and ensur…

Adversarial Robustness

A Unified Algebraic Perspective on Lipschitz Neural Networks

2023-03-06 · ICLR 2023 2 · Alexandre Araujo, Aaron Havens, Blaise Delattre, Alexandre Allauzen 외

Important research efforts have focused on the design and training of neural networks with a controlled Lipschitz constant. The goal is to increase and sometimes guarantee the robustness against adversarial attacks. Rece…

image-classificationImage ClassificationProvable Adversarial Defense

Enhancing Certified Robustness via Block Reflector Orthogonal Layers and Logit Annealing Loss

2025-05-21 · Bo-Han Lai, Pin-Han Huang, Bo-Han Kung, Shang-Tse Chen

Lipschitz neural networks are well-known for providing certified robustness in deep learning. In this paper, we present a novel, efficient Block Reflector Orthogonal (BRO) layer that enhances the capability of orthogonal…

Almost-Orthogonal Layers for Efficient General-Purpose Lipschitz Networks

2022-08-05 · Bernd Prach, Christoph H. Lampert

It is a highly desirable property for deep networks to be robust against small input changes. One popular way to achieve this property is by designing networks with a small Lipschitz constant. In this work, we propose a …

image-classificationImage Classification

Preventing Gradient Attenuation in Lipschitz Constrained Convolutional Networks

2019-11-03 · NeurIPS 2019 12 · Qiyang Li, Saminul Haque, Cem Anil, James Lucas 외

Lipschitz constraints under L2 norm on deep neural networks are useful for provable adversarial robustness bounds, stable training, and Wasserstein distance estimation. While heuristic approaches such as the gradient pen…

Adversarial Robustness