优化的Kolmogorov-Arnold网络架构
Optimized Architectures for Kolmogorov-Arnold Networks
AI总结：
本文提出通过过度配置架构结合稀疏化、深度监督和深度选择，学习紧凑且可解释的KANs，同时保持准确性。
摘要：
为改进Kolmogorov-Arnold网络（KANs）的架构而进行的努力一直受到这些增强所带来的复杂性所阻碍，削弱了使KANs在最初具有吸引力的可解释性。本文研究了过度配置的架构结合稀疏化、深度监督和深度选择，以学习紧凑且可解释的KANs，同时不牺牲准确性。关键在于在基于原理的最小描述长度目标下，采用可微的机制，联合优化激活、结构和深度。在函数逼近基准、动态系统预测和现实世界预测任务中的实验表明，稀疏化单独是不够的，但结合深度选择可以实现竞争或更优的准确性，同时发现显著更小的模型。结果是一种有原则的路径，使模型在表达性和可解释性上都得到提升，解决科学机器学习中的关键矛盾。
英文摘要：
Efforts to improve Kolmogorov--Arnold networks (KANs) with architectural enhancements have been stymied by the complexity those enhancements bring, undermining the interpretability that makes KANs attractive in the first place. Here we study overprovisioned architectures combined with sparsification, deep supervision, and depth selection, to learn compact, interpretable KANs without sacrificing accuracy. Crucially, we focus on differentiable mechanisms under a principled minimum description length objective, jointly optimizing activations, structure, and depth end-to-end. Experiments across function approximation benchmarks, dynamical systems forecasting, and real-world prediction tasks demonstrate that sparsification alone is insufficient, but the combination with depth selection achieves competitive or superior accuracy while discovering substantially smaller models. The result is a principled path toward models that are both more expressive and more interpretable, addressing a key tension in scientific machine learning.
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。
