Ultrafast On-chip Online Learning via Spline Locality in Kolmogorov-Arnold Networks

TL;DR

This paper introduces a novel on-chip online learning method using Kolmogorov-Arnold Networks that achieves sub-microsecond adaptation speeds suitable for high-frequency systems, outperforming traditional neural networks in efficiency and stability.

Contribution

The work demonstrates that KANs with spline locality enable ultrafast, resource-efficient online learning on FPGAs, a first in achieving sub-microsecond model-free adaptation.

Findings

KAN updates are sparse due to spline locality, improving resource scaling.

KANs are robust to fixed-point quantization, enhancing stability.

Fixed-point FPGA implementation shows superior efficiency and expressiveness.

Abstract

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.