Variational Quantum Integrated Sensing and Communication

TL;DR

The paper tackles the problem of jointly achieving high classical data rates and accurate parameter sensing in a quantum setting by proposing QISAC, a protocol that uses entangled two-qudit probes to support both superdense coding and sensing. It introduces an end-to-end variational framework where a parameterized quantum circuit at the receiver, together with classical neural decoders and estimators, is trained to maximize a weighted objective over decoding success $P_{\text{succ}}$ and sensing accuracy $P_{\text{acc}}$. Experimental results on $d=8,10$ qudits with a discrete four-value parameter show a tunable trade-off: increasing rate back-off $\Delta B$ lowers sensing accuracy, while the variational receiver outperforms conventional Bell-measurement schemes, achieving comparable throughput with higher $P_{\text{acc}}$ at intermediate back-off. The work demonstrates a practical near-term pathway to quantum ISAC and points to future directions such as continuous/multi-parameter sensing and robustness to noise.

Abstract

The integration of sensing and communication functionalities within a common system is one of the main innovation drivers for next-generation networks. In this paper, we introduce a quantum integrated sensing and communication (QISAC) protocol that leverages entanglement in quantum carriers of information to enable both superdense coding and quantum sensing. The proposed approach adaptively optimizes encoding and quantum measurement via variational circuit learning, while employing classical machine learning-based decoders and estimators to process the measurement outcomes. Numerical results for qudit systems demonstrate that the proposed QISAC protocol can achieve a flexible trade-off between classical communication rate and accuracy of parameter estimation.

Figures (2)

• Figure 1: Proposed QISAC protocol: Charlie generates a probe quantum state consisting of two qudits, and distributes the two qudits to Alice and Bob. Alice encodes her message $m$ via a unitary transformation $U(m)$ following superdense coding, and her qudit is sent via the channel, interacting with the parameter of interest, $x$. Bob receives the qudit sent by Alice, applies a decoding unitary $U(\mu)$, and measures the qudit obtain a measurement sample $s$. The protocol uses a classical decoder and estimator which produce the decoded message $\hat{m}$ and the estimate $\hat{x}$, respectively, using the measurement outcome.
• Figure 2: Communication throughput (bits per channel use) versus probability of accurate sensing estimation for $d=8$ (left) and $d=10$ (right). The curves are obtained by varying the communication back-off from $\Delta B=0$ to $\Delta B= B_{\max}$.