We present a novel algorithm for parameter learning in generic deep generative models that builds upon the predictive coding (PC) framework of computational neuroscience. Our approach modifies the standard PC algorithm to bring performance on-par and exceeding that obtained from standard variational auto-encoder (VAE) training. By injecting Gaussian noise into the PC inference procedure we re-envision it as an overdamped Langevin sampling, which facilitates optimisation with respect to a tight evidence lower bound (ELBO). We improve the resultant encoder-free training method by incorporating an encoder network to provide an amortised warm-start to our Langevin sampling and test three different objectives for doing so. Finally, to increase robustness to the sampling step size and reduce sensitivity to curvature, we validate a lightweight and easily computable form of preconditioning, inspired by Riemann Manifold Langevin and adaptive optimizers from the SGD literature. We compare against VAEs by training like-for-like generative models using our technique against those trained with standard reparameterisation-trick-based ELBOs. We observe our method out-performs or matches performance across a number of metrics, including sample quality, while converging in a fraction of the number of SGD training iterations.

翻译：我们提出了一种新颖的算法，用于通用深度生成模型中的参数学习，该算法建立在计算神经科学的预测编码（PC）框架之上。我们的方法修改了标准PC算法，使其性能达到甚至超过标准变分自编码器（VAE）训练所获得的结果。通过在PC推断过程中注入高斯噪声，我们将其重新构想为一种过阻尼朗之万采样，这有助于优化紧致的证据下界（ELBO）。我们通过引入编码器网络来改进最终的无编码器训练方法，为我们的朗之万采样提供摊销化的热启动，并测试了三种不同的目标函数来实现这一点。最后，为了增强对采样步长的鲁棒性并降低对曲率的敏感性，我们验证了一种轻量级且易于计算的预条件形式，其灵感来源于黎曼流形朗之万方法和SGD文献中的自适应优化器。我们通过使用我们的技术训练同类生成模型，并与使用标准重参数化技巧ELBO训练的VAE进行比较。我们观察到，我们的方法在多个指标（包括样本质量）上优于或匹配现有性能，同时仅需SGD训练迭代次数的一小部分即可收敛。