Assessing the Impact of Low Resolution Control Electronics on Quantum Neural Network Performance

TL;DR

This study shows that quantum neural networks can be effectively trained and deployed with low-resolution control electronics (4-10 bits), maintaining high accuracy and enabling power-efficient quantum hardware scaling.

Contribution

We introduce a stochastic quantization method that allows successful training of QNNs at low DAC resolutions, surpassing previous limitations and matching infinite-precision performance.

Findings

Pre-trained QNNs perform nearly as well with 6-bit DACs as with infinite precision.

Gradient deadlock occurs below 12-bit resolution during training.

Stochastic quantization enables effective training at 4-10 bits, often exceeding baseline performance.

Abstract

Scaling quantum computers requires tight integration of cryogenic control electronics with quantum processors, where Digital-to-Analog Converters (DACs) face severe power and area constraints. We investigate quantum neural network (QNN) training and inference under finite DAC resolution constraints, evaluating two QNN architectures across four diverse datasets (MNIST, Fashion-MNIST, Iris, Breast Cancer). Pre-trained QNNs achieve accuracy nearly indistinguishable from infinite-precision baselines when deployed on quantum systems with 6-bit DAC control electronics, exhibiting characteristic elbow curves with diminishing returns beyond 3-5 bits depending on the dataset. However, training QNNs directly under quantization constraints reveals gradient deadlock below 12-bit resolution, where parameter updates fall below quantization step sizes, preventing training entirely. We introduce temperature-controlled stochastic quantization that overcomes this limitation through probabilistic parameter updates, enabling successful training at 4-10 bit resolutions. Remarkably, stochastic quantization not only matches but frequently exceeds infinite-precision baseline performance across both architectures and all datasets. Our findings demonstrate that low-resolution control electronics (4-10 bits) need not compromise QML performance while enabling substantial power and area reduction in cryogenic control systems, presenting significant implications for practical quantum hardware scaling and hardware-software co-design of QML systems.