对比Ising与QUBO编码对玻尔兹曼机学习效率的影响
Performance Evaluation of Ising and QUBO Variable Encodings in Boltzmann Machine Learning
- 基于相同模型和采样器，比较两种变量编码的统计特性差异
- QUBO编码导致更差的梯度条件，使SGD收敛变慢
- 自然梯度法可克服编码差异，适合对编码敏感的任务
我们在固定模型、采样器和步长的受控协议下，比较了玻尔兹曼机学习中Ising（{-1,+1}）与QUBO（{0,1}）编码的性能。利用费雪信息矩阵（FIM）等于充分统计量协方差的性质，我们可视化了模型样本的实证矩，揭示出系统性、依赖表示的差异。QUBO编码引入了第一阶与第二阶统计量之间的更大交叉项，导致FIM中出现更多小特征值方向，降低谱熵。这种病态条件解释了在随机梯度下降（SGD）下收敛更慢的现象。相比之下，自然梯度下降（NGD）——通过FIM度量重缩放更新——由于参数化不变性，在不同编码下均实现相似收敛速度。实践中，对于基于SGD的训练，Ising编码提供更各向同性的曲率，收敛更快；而对于QUBO编码，中心化/缩放或类似NGD的预处理可缓解曲率问题。这些结果阐明了表示如何影响玻尔兹曼机的信息几何与有限时间学习动态，并提供了变量编码与预处理的实际指导。
原文摘要 · Abstract (English)
We compare Ising ({-1,+1}) and QUBO ({0,1}) encodings for Boltzmann machine learning under a controlled protocol that fixes the model, sampler, and step size. Exploiting the identity that the Fisher information matrix (FIM) equals the covariance of sufficient statistics, we visualize empirical moments from model samples and reveal systematic, representation-dependent differences. QUBO induces larger cross terms between first- and second-order statistics, creating more small-eigenvalue directions in the FIM and lowering spectral entropy. This ill-conditioning explains slower convergence under stochastic gradient descent (SGD). In contrast, natural gradient descent (NGD)-which rescales updates by the FIM metric-achieves similar convergence across encodings due to reparameterization invariance. Practically, for SGD-based training, the Ising encoding provides more isotropic curvature and faster convergence; for QUBO, centering/scaling or NGD-style preconditioning mitigates curvature pathologies. These results clarify how representation shapes information geometry and finite-time learning dynamics in Boltzmann machines and yield actionable guidelines for variable encoding and preprocessing.
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。