---
title: "GFlowQEC: Generative Flow Networks that Learn to Sample Quantum LDPC Codes"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2611.06819v1"
permalink: "https://feed.astralor.com/items/itm_33273021c0f42a41c8655a10"
published: "2026-11-04T17:31:57.000Z"
score: 60
channel: "finance"
tags: ["GFlowQEC","Generative Flow Networks","Learn","Sample Quantum LDPC","Codes Choosing","Choosing","Quantum LDPC"]
---

# GFlowQEC: Generative Flow Networks that Learn to Sample Quantum LDPC Codes

## At a glance

Choosing a quantum error-correcting code for a real device means scoring candidates with circuit-level simulations so slow that only a few hundred can be run. So every evaluation counts, and a search is judged by how ma…

## Key points

- Choosing a quantum error-correcting code for a real device means scoring candidates with circuit-level simulations so slow that only a few hundred can be run.
- So every evaluation counts, and a search is judged by how many good codes it finds per paid evaluation.
- Quantum LDPC codes built from a few group elements protect many logical qubits, but good ones are rare in a huge space.

## Full text

Choosing a quantum error-correcting code for a real device means scoring candidates with circuit-level simulations so slow that only a few hundred can be run. So every evaluation counts, and a search is judged by how many good codes it finds per paid evaluation. Quantum LDPC codes built from a few group elements protect many logical qubits, but good ones are rare in a huge space. We introduce GFlowQEC, to our knowledge the first generative flow network (GFlowNet) for quantum code design. It builds a code one group element at a time and learns to propose codes in proportion to a power of their score. We train it once on scores from earlier searches, freeze it, and let it propose lifted-product codes with 180 physical qubits, scored by their distances. Ranking ten of its draws per paid call, it finds more than twice as many new top-scoring codes (inequivalent to any it was trained on) as tuned parallel tempering, even when tempering starts from GFlowQEC's training codes. It finds more than three and a half times as many as a supervised screen ranking ten random candidates per call. When both rank a hundred, the screen beats GFlowQEC, and does best ranking GFlowQEC's draws. Soft Q-learning, which shares the GFlowNet's optimal policy, does as well at one noise bias and better at the other, so the gain does not depend on the GFlowNet's training loss. Trained proposers can make a budget of expensive evaluations go further when good codes are rare.

---

Verify against the original before citing; curated by Astral Feed: https://feed.astralor.com/items/itm_33273021c0f42a41c8655a10