Mean estimation in high-dimensional binary timeinhomogeneous Markov Gaussian mixture models

We explore the problem of mean estimation for a high-dimensional binary symmetric Gaussian mixture model, where the label (sign) follows a time-inhomogeneous Markov chain. We propose a spectral estimator based on a partition of a subset of the samples to blocks. We develop a computationally efficient algorithm to find the optimal blocks, and derive minimax lower bounds on the estimation loss of any estimator, which establish the effectiveness of our proposed estimator. The resulting minimax rate illuminates the interplay between the sample size, dimension, signal strength, and the memory on the loss.