The Relative Complexity of Maximum Likelihood Estimation, MAP Estimation, and Sampling.
COLT(2019)
摘要
We prove that, for a broad range of problems, maximum-a-posteriori (MAP) estimation and approximate sampling of the posterior are at least as computationally difficult as maximum-likelihood (ML) estimation. By way of illustration, we show how hardness results for ML estimation of mixtures of Gaussians and topic models carry over to MAP estimation and approximate sampling under commonly used priors.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络