论文标题
量化变异推断
Quantized Variational Inference
论文作者
论文摘要
我们提出了量化的变异推断，这是一种用于证据下限最大化的新算法。我们展示了最佳的Voronoi Tesselation如何以渐近衰减的偏差为代价产生无方差梯度来优化ELBO优化。随后，我们提出了一种理查森外推类型方法来改善渐近结合。我们表明，使用量化的变异推理框架会导致分数函数和重新处理梯度估计器的快速收敛，以相当的计算成本。最后，我们提出了几个实验，以评估我们的方法的性能及其局限性。
We present Quantized Variational Inference, a new algorithm for Evidence Lower Bound maximization. We show how Optimal Voronoi Tesselation produces variance free gradients for ELBO optimization at the cost of introducing asymptotically decaying bias. Subsequently, we propose a Richardson extrapolation type method to improve the asymptotic bound. We show that using the Quantized Variational Inference framework leads to fast convergence for both score function and the reparametrized gradient estimator at a comparable computational cost. Finally, we propose several experiments to assess the performance of our method and its limitations.
