arXiv:2609.19783
Scalable entanglement distribution using encoded hybrid repeater chains
Stav Haldar, Saikat Guha, Don Towsley, Filip Rozpędek
Abstract
Long-distance entanglement distribution requires error correction protocols to compensate for qubit decoherence in quantum memories and noise introduced during entanglement swapping. We argue that repeater chains with error-correction capabilities should exploit more than one physical platform, combining the complementary strengths of different quantum memory technologies into a single hybrid repeater architecture. An important constituent of such an architecture is a hybrid repeater which combines type-1 memories, characterized by fast entanglement generation rates and suitability for multiplexing, and type-2 memories that offer long coherence times and low two-qubit gate error rates. Taking the resource-intensive nature of hybrid nodes into account, we propose and analyze repeater chains in which only a subset of nodes need to be hybrid, while the remaining nodes are simpler first-generation repeaters with no error-correction capability. Through detailed Monte Carlo simulations of fault-tolerant encoded repeater chain protocols based on the three-qubit phase-flip repetition code, the $[[7,1,3]]$ Steane code, and the $[[9,1,3]]$ Shor code, we demonstrate that these hybrid architectures outperform pure architectures based on a single memory platform in terms of end-to-end entanglement distribution rate. In our study we develop a full circuit-level noise model of our architectures and examine the impact of an imperfect interface between the two platforms on our hybrid architecture. We also develop a modified version of the swap-as-soon-as-possible policy with multiplexing, more suited to our architecture where some nodes perform error-correction while others do not. This modified policy significantly reduces the information storage time in memory qubits relative to the previously considered swap policies in encoded repeater chains.
AI Summary
The paper asks whether long-distance encoded repeater chains benefit from combining fast, multiplexable but noisier memories with slower memories offering longer coherence and better gates, and whether error-correcting nodes can be deployed sparsely. It compares homogeneous chains with hybrid chains using the first platform for link generation and the second for encoding and swapping, with simpler non-error-correcting nodes between hybrid nodes. Monte Carlo simulations track stochastic link generation and storage times; gate counts and approximate physical-to-logical error formulas estimate fidelity for three-qubit phase-flip repetition, Steane $[[7,1,3]]$, and Shor $[[9,1,3]]$ codes. Performance is quantified by a Bell-diagonal hashing-bound entanglement rate. With 20-km spacing, type-1 coherence of 50 ms, and tenfold platform contrasts in multiplexing, coherence and gate error, hybrid chains outperform homogeneous baselines in the reported low-to-moderate-error regimes. At 960 km, placing hybrid nodes every second hop gives rates comparable to homogeneous type-2 chains while using approximately one-quarter as many type-2 memories. For the studied distance sweep, encoding becomes advantageous around 1600 km. Hybrid advantages with Steane and Shor codes persist with inter-platform gate error $5\times10^{-4}$. A deferred-consumption swap-ASAP policy preserves multiplexing between error-correcting nodes and reduces storage relative to waiting for all links. Limitations include abstract platform parameters, assumed direct inter-platform gates, neglected gate and measurement durations and some classical-communication costs, and approximate error accounting rather than explicit syndrome simulation. Platform-specific implementations, higher-distance codes and policy optimization remain open.
Central claim may not hold: The advertised full circuit-level noise treatment is not established by the described gate-count, endpoint-splitting, and truncated logical-error approximations. Replacing the specified correlated two-qubit depolarizing channel by independent marginals loses first-order joint faults, contrary to the paper's explicit claim, leaving the quantitative encoded-rate comparisons insufficiently validated. The stated time-step formula gives approximately 100 microseconds at 20 km and 500 steps per 50 ms, inconsistent with the 150 microseconds and 333 steps used in Results. The main text and appendix prescribe different increments and triggering events for classical-communication-induced memory aging, leaving the simulated timing model ambiguous.
Written by gpt-6.1-sol from the paper's full text. Automated: it can be wrong.
- Comments
- 28 pages main text (plus 14 pages Appendix), 12 figures. Comments are welcome