Statistical inference with implicit SGD: proximal Robbins-Monro vs. Polyak-Ruppert
The implicit stochastic gradient descent (ISGD), a proximal version of SGD, is gaining interest in the literature due to its stability over (explicit) SGD. In this paper, we conduct an in-depth analysis of the two modes of ISGD for smooth convex functions, namely proximal Robbins-Monro (proxRM) and proximal Poylak-Ruppert (proxPR) procedures, for their use in statistical inference on model parameters. Specifically, we derive non-asymptotic point estimation error bounds of both proxRM and proxPR iterates and their limiting distributions, and propose on-line estimators of their asymptotic covariance matrices that require only a single run of ISGD. The latter estimators are used to construct valid confidence intervals for the model parameters. Our analysis is free of the generalized linear model assumption that has limited the preceding analyses, and employs feasible procedures. Our on-line covariance matrix estimators appear to be the first of this kind in the ISGD literature.
Code (0)
등록된 구현이 없습니다.
Tasks
validMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
The Proximal Robbins-Monro Method
The need for parameter estimation with massive datasets has reinvigorated interest in stochastic optimization and iterative estimation procedures. Stochastic approximations are at the forefront of this recent development…
parameter estimationStochastic OptimizationA Robbins--Monro Sequence That Can Exploit Prior Information For Faster Convergence
We propose a new method to improve the convergence speed of the Robbins-Monro algorithm by introducing prior information about the target point into the Robbins-Monro iteration. We achieve the incorporation of prior info…
DS FedProxGrad: Asymptotic Stationarity Without Noise Floor in Fair Federated Learning
Recent work \cite{arifgroup} introduced Federated Proximal Gradient \textbf{(\texttt{FedProxGrad})} for solving non-convex composite optimization problems in group fair federated learning. However, the original analysis …
Federated LearningRobbins-Monro conditions for persistent exploration learning strategies
We formulate simple assumptions, implying the Robbins-Monro conditions for the $Q$-learning algorithm with the local learning rate, depending on the number of visits of a particular state-action pair (local clock) and th…
Q-LearningLearning to Schedule Online Tasks with Bandit Feedback
Online task scheduling serves an integral role for task-intensive applications in cloud computing and crowdsourcing. Optimal scheduling can enhance system performance, typically measured by the reward-to-cost ratio, unde…
Cloud ComputingDecision MakingScheduling