改进离散隐变量梯度估计，降低训练波动性
Beyond ReinMax: Low-Variance Gradient Estimators for Discrete Latent Variables
- 在ReinMax基础上引入降方差技术，提升稳定性
- 在离散变分自编码器上实现更优训练性能
- 适合需要稳定训练的离散潜空间模型研究者
包含离散隐变量的机器学习模型需依赖梯度估计以实现高效反向传播。最新提出的直通族估计算法ReinMax可从数值常微分方程视角理解为使用Heun方法近似以降低偏差，但伴随高方差问题。本文提出ReinMax-Rao与ReinMax-CV两种新估计器，分别融合Rao-Blackwellisation与控制变量技术，有效降低其方差。实验表明，这些方法在离散潜空间变分自编码器训练中表现更优。此外，我们探讨了采用其他数值方法构建更精确梯度近似的可能性，并从更简单的数值积分角度重新诠释ReinMax。
原文摘要 · Abstract (English)
Machine learning models involving discrete latent variables require gradient estimators to facilitate backpropagation in a computationally efficient manner. The most recent addition to the Straight-Through family of estimators, ReinMax, can be viewed from a numerical ODE perspective as incorporating an approximation via Heun's method to reduce bias, but at the cost of high variance. In this work, we introduce the ReinMax-Rao and ReinMax-CV estimators which incorporate Rao-Blackwellisation and control variate techniques into ReinMax to reduce its variance. Our estimators demonstrate superior performance on training variational autoencoders with discrete latent spaces. Furthermore, we investigate the possibility of leveraging alternative numerical methods for constructing more accurate gradient approximations and present an alternative view of ReinMax from a simpler numerical integration perspective.
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。