Floating-floating point: a highly accurate number representation with flexible Counting ranges
This addresses efficiency challenges in applications like federated learning and network measurement that use narrow bit-width systems, offering an incremental improvement over existing methods.
The paper tackles the trade-off between counting range and accuracy in narrow bit-width floating-point systems by introducing Floating-Floating-Point (F2P), which varies the mantissa-exponent partition to achieve a large counting range with improved accuracy in selected sub-ranges, resulting in enhanced network measurement accuracy and federated learning performance.
Efficient number representation is essential for federated learning, natural language processing, and network measurement solutions. Due to timing, area, and power constraints, such applications use narrow bit-width (e.g., 8-bit) number systems. The widely used floating-point systems exhibit a trade-off between the counting range and accuracy. This paper introduces Floating-Floating-Point (F2P) - a floating point number that varies the partition between mantissa and exponent. Such flexibility leads to a large counting range combined with improved accuracy over a selected sub-range. Our evaluation demonstrates that moving to F2P from the state-of-the-art improves network measurement accuracy and federated learning.