基于Kolmogorov-Arnold网络中样条局部性的超快片上在线学习
Ultrafast On-Chip Online Learning via Spline Locality in Kolmogorov-Arnold Networks
AI总结：
针对量子计算和核聚变控制等高频系统对亚微秒级在线学习的需求，提出利用Kolmogorov-Arnold网络的B样条局部性实现稀疏更新和固定点量化鲁棒性，在FPGA上实现比MLP更高效、更具表达力的超快在线学习。
摘要：
超快在线学习对于高频系统（如量子计算和核聚变控制）至关重要，这些系统中的自适应必须在亚微秒时间尺度内发生。满足这些需求需要在严格的内存约束下进行低延迟、固定精度的计算，而传统的多层感知器（MLP）在这种条件下既低效又不稳定。我们识别了Kolmogorov-Arnold网络（KAN）与这些约束相符的关键特性。具体来说，我们表明：（i）利用B样条局部性的KAN更新是稀疏的，从而实现优越的片上资源缩放；（ii）KAN对固定点量化具有固有的鲁棒性。通过在现场可编程门阵列（FPGA）上实现固定点在线训练（一种代表性的片上计算平台），我们证明基于KAN的在线学习器在一系列低延迟和资源受限的任务中比MLP显著更高效且更具表达力。据我们所知，这项工作首次展示了在亚微秒延迟下的无模型在线学习。
英文摘要：
Ultrafast online learning is essential for high-frequency systems, such as controls for quantum computing and nuclear fusion, where adaptation must occur on sub-microsecond timescales. Meeting these requirements demands low-latency, fixed-precision computation under strict memory constraints, a regime in which conventional Multi-Layer Perceptrons (MLPs) are both inefficient and numerically unstable. We identify key properties of Kolmogorov-Arnold Networks (KANs) that align with these constraints. Specifically, we show that: (i) KAN updates exploiting B-spline locality are sparse, enabling superior on-chip resource scaling, and (ii) KANs are inherently robust to fixed-point quantization. By implementing fixed-point online training on Field-Programmable Gate Arrays (FPGAs), a representative platform for on-chip computation, we demonstrate that KAN-based online learners are significantly more efficient and expressive than MLPs across a range of low-latency and resource-constrained tasks. To our knowledge, this work is the first to demonstrate model-free online learning at sub-microsecond latencies.
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。
