4 papers · 1 filter
A Piecewise Lyapunov Analysis of Sub-quadratic SGD: Applications to Robust and Quantile Regression
Yixuan Zhang, Dongyan Huo, Yudong Chen +1
Motivated by robust and quantile regression problems, we investigate the stochastic gradient descent (SGD) algorithm for minimizing an objective function that is locally strong…
The Collusion of Memory and Nonlinearity in Stochastic Approximation With Constant Stepsize
Dongyan Huo, Yixuan Zhang, Yudong Chen +1
In this work, we investigate stochastic approximation (SA) with Markovian data and nonlinear updates under constant stepsize . Existing work has primarily focused on either i.…
Prelimit Coupling and Steady-State Convergence of Constant-stepsize Nonsmooth Contractive SA
Yixuan Zhang, Dongyan Huo, Yudong Chen +1
Motivated by Q-learning, we study nonsmooth contractive stochastic approximation (SA) with constant stepsize. We focus on two important classes of dynamics: 1) nonsmooth contractiv…
Effectiveness of Constant Stepsize in Markovian LSA and Statistical Inference
Dongyan Huo, Yudong Chen, Qiaomin Xie
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 esta…