SequeL：一个基于 PyTorch 和 JAX 的持续学习库
SequeL: A Continual Learning Library in PyTorch and JAX
AI总结：
本文提出同时支持 PyTorch 与 JAX 的开源持续学习库 SequeL，通过统一接口集成正则化、回放及混合算法，提升模块化、可复现性与可扩展性。
摘要：
持续学习是机器学习中一个重要且具有挑战性的问题，模型必须适应连续不断的新数据流，同时不遗忘先前获得的知识。现有框架基于 PyTorch 构建，而 JAX 日益流行可能导致代码库分化，最终阻碍可复现性和研究进展。为解决这一问题，我们推出 SequeL，这是一个灵活且可扩展的持续学习库，同时支持 PyTorch 和 JAX 框架。SequeL 为广泛的持续学习算法提供统一接口，包括基于正则化的方法、基于回放的方法以及混合方法。该库以模块化和简洁性为设计目标，使其 API 同时适合研究人员和从业者。我们将 SequeL 作为开源库发布，使研究人员和开发者能够轻松开展实验，并根据自身需求扩展该库。
英文摘要：
Continual Learning is an important and challenging problem in machine learning, where models must adapt to a continuous stream of new data without forgetting previously acquired knowledge. While existing frameworks are built on PyTorch, the rising popularity of JAX might lead to divergent codebases, ultimately hindering reproducibility and progress. To address this problem, we introduce SequeL, a flexible and extensible library for Continual Learning that supports both PyTorch and JAX frameworks. SequeL provides a unified interface for a wide range of Continual Learning algorithms, including regularization-based approaches, replay-based approaches, and hybrid approaches. The library is designed towards modularity and simplicity, making the API suitable for both researchers and practitioners. We release SequeL\footnote{\url{https://github.com/nik-dim/sequel}} as an open-source library, enabling researchers and developers to easily experiment and extend the library for their own purposes.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
