Multiscale Invertible Generative Networks for High-Dimensional Bayesian Inference
Multiscale Invertible Generative Networks for High-Dimensional Bayesian Inference
复制标题
DOI：
--
复制
发表时间：
2021-05
期刊：
影响因子：
--
通讯作者：
Shumao Zhang;Pengchuan Zhang;T. Hou
中科院分区：
文献类型：
--
作者：
Shumao Zhang;Pengchuan Zhang;T. Hou
我们提出了一个多尺度可逆生成网络（MsIGN）和相关的训练算法，利用多尺度结构来解决高维贝叶斯推理。为了解决维数灾难，MsIGN利用后验的低维性质，并通过迭代上采样和细化样本来生成从粗到细（低到高维）的样本。MsIGN以多阶段的方式进行训练，以最大限度地减少Jeffreys发散，从而避免在高维情况下的模式下降。两个高维贝叶斯逆问题，我们表现出上级性能的MsIGN比以前的方法在后验近似和多模式捕获。在自然图像合成任务中，MsIGN在每维比特数上实现了优于基线模型的上级性能，并在中间层中产生了很好的神经元解释能力。
We propose a Multiscale Invertible Generative Network (MsIGN) and associated training algorithm that leverages multiscale structure to solve high-dimensional Bayesian inference. To address the curse of dimensionality, MsIGN exploits the low-dimensional nature of the posterior, and generates samples from coarse to fine scale (low to high dimension) by iteratively upsampling and refining samples. MsIGN is trained in a multi-stage manner to minimize the Jeffreys divergence, which avoids mode dropping in high-dimensional cases. On two high-dimensional Bayesian inverse problems, we show superior performance of MsIGN over previous approaches in posterior approximation and multiple mode capture. On the natural image synthesis task, MsIGN achieves superior performance in bits-per-dimension over baseline models and yields great interpret-ability of its neurons in intermediate layers.