Stability and Generalization for Markov Chain Stochastic Gradient Methods
This provides theoretical guarantees for MC-SGMs in statistical learning, addressing a gap in generalization analysis for gradient sampling from Markov processes.
The paper tackles the generalization analysis of Markov chain stochastic gradient methods (MC-SGMs) for minimization and minimax problems, establishing optimal excess population risk bounds for empirical risk minimization and nearly optimal convergence rates for convex-concave problems.
Recently there is a large amount of work devoted to the study of Markov chain stochastic gradient methods (MC-SGMs) which mainly focus on their convergence analysis for solving minimization problems. In this paper, we provide a comprehensive generalization analysis of MC-SGMs for both minimization and minimax problems through the lens of algorithmic stability in the framework of statistical learning theory. For empirical risk minimization (ERM) problems, we establish the optimal excess population risk bounds for both smooth and non-smooth cases by introducing on-average argument stability. For minimax problems, we develop a quantitative connection between on-average argument stability and generalization error which extends the existing results for uniform stability \cite{lei2021stability}. We further develop the first nearly optimal convergence rates for convex-concave problems both in expectation and with high probability, which, combined with our stability results, show that the optimal generalization bounds can be attained for both smooth and non-smooth cases. To the best of our knowledge, this is the first generalization analysis of SGMs when the gradients are sampled from a Markov process.