用自编码器找到费米子基态的最小压缩表示,突破传统量子态约束难题。
Learning Minimal Representations of Fermionic Ground States
- 用神经网络自编码器学习费米子系统的最小隐空间表示。
- 在L-1维隐空间实现精确重构,与系统自由度一致。
- 可直接在隐空间优化能量,避免物理不可行态问题,适合量子模拟研究者。
我们提出一种无监督机器学习框架,用于发现量子多体基态的最优压缩表示。基于L个格点的费米-哈伯德模型数据,采用自编码器神经网络架构,识别出具有尖锐重构质量阈值的最小隐空间,其维度恰好为L-1,与系统的内在自由度一致。我们展示了训练后的解码器可作为可微分的变分波函数,在隐空间中直接最小化能量。关键优势在于该方法规避了N-可表示性问题,因为学习到的流形隐式限制优化过程仅在物理上合理的量子态范围内进行。
原文摘要 · Abstract (English)
We introduce an unsupervised machine-learning framework that discovers optimally compressed representations of quantum many-body ground states. Using an autoencoder neural network architecture on data from $L$-site Fermi-Hubbard models, we identify minimal latent spaces with a sharp reconstruction quality threshold at $L-1$ latent dimensions, matching the system's intrinsic degrees of freedom. We demonstrate the use of the trained decoder as a differentiable variational ansatz to minimize energy directly within the latent space. Crucially, this approach circumvents the $N$-representability problem, as the learned manifold implicitly restricts the optimization to physically valid quantum states.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品;中文卡片由大模型生成,请以原文为准。