Effectiveness of Constant Stepsize in Markovian LSA and Statistical Inference
This work addresses the challenge of efficient and reliable statistical inference for practitioners dealing with Markovian data, offering an incremental improvement over classical methods.
The paper tackles the problem of statistical inference using linear stochastic approximation with Markovian data by proposing a constant stepsize approach, which results in easier hyperparameter tuning, faster convergence, and consistently better confidence interval coverage, especially with limited data.
In this paper, we study the effectiveness of using a constant stepsize in statistical inference via linear stochastic approximation (LSA) algorithms with Markovian data. After establishing a Central Limit Theorem (CLT), we outline an inference procedure that uses averaged LSA iterates to construct confidence intervals (CIs). Our procedure leverages the fast mixing property of constant-stepsize LSA for better covariance estimation and employs Richardson-Romberg (RR) extrapolation to reduce the bias induced by constant stepsize and Markovian data. We develop theoretical results for guiding stepsize selection in RR extrapolation, and identify several important settings where the bias provably vanishes even without extrapolation. We conduct extensive numerical experiments and compare against classical inference approaches. Our results show that using a constant stepsize enjoys easy hyperparameter tuning, fast convergence, and consistently better CI coverage, especially when data is limited.