打造高效统一的正交与1-Lipschitz层库，提升模型鲁棒性与稳定性
Orthogonium : A Unified, Efficient Library of Orthogonal and 1-Lipschitz Building Blocks
- 整合正交与1-Lipschitz层，支持卷积多种参数配置
- 在ImageNet等大尺度基准上显著降低计算开销
- 修复现有实现缺陷，助力可靠模型研发
正交与1-Lipschitz神经网络层是构建鲁棒深度学习架构的关键组件，对认证对抗鲁棒性、稳定生成模型和可靠递归网络至关重要。尽管已有显著进展，现有实现仍分散、受限且计算成本高。为此，我们提出Orthogonium，一个统一、高效、全面的PyTorch库，提供正交与1-Lipschitz层。该库支持标准卷积特性，包括步幅、膨胀、分组和转置卷积，同时保持严格的数学保证。其优化实现显著降低了ImageNet等大规模基准上的开销。此外，库内严格测试发现了现有实现中的关键错误，凸显了标准化可靠工具的重要性。Orthogonium大幅降低使用门槛，支持跨多种需正交性和鲁棒Lipschitz约束的应用场景的可扩展实验与集成。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。