让深度学习模型轻松实现带约束优化
Cooper: A Library for Constrained Optimization in Deep Learning
- 基于拉格朗日方法设计一阶更新算法
- 无缝集成PyTorch的自动微分与架构
- 适合需要约束训练的深度学习研究者
Cooper是一个开源库，用于解决涉及深度学习模型的约束优化问题。它实现了多种基于拉格朗日的梯度下降更新策略，使约束优化算法能与PyTorch的高级特性（如自动微分、专用网络架构和优化器）轻松结合。尽管Cooper专为基于小批量梯度估计的深度学习场景设计，但也可用于一般的非凸连续约束优化问题。其源代码可在https://github.com/cooper-org/cooper获取。
原文摘要 · Abstract (English)
Cooper is an open-source package for solving constrained optimization problems involving deep learning models. Cooper implements several Lagrangian-based first-order update schemes, making it easy to combine constrained optimization algorithms with high-level features of PyTorch such as automatic differentiation, and specialized deep learning architectures and optimizers. Although Cooper is specifically designed for deep learning applications where gradients are estimated based on mini-batches, it is suitable for general non-convex continuous constrained optimization. Cooper's source code is available at https://github.com/cooper-org/cooper.
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。