Simple and Optimal Methods for Stochastic Variational Inequalities, I: Operator Extrapolation
نویسندگان
چکیده
In this paper we first present a novel operator extrapolation (OE) method for solving deterministic variational inequality (VI) problems. Similar to the gradient (operator) projection method, OE updates one single search sequence by subproblem in each iteration. We show that can achieve optimal rate of convergence variety VI problems much simpler way than existing approaches. then introduce stochastic (SOE) and establish its behavior various particular, SOE achieves complexity fundamental problem, i.e., smooth strongly monotone VI, time literature. also block further reduce iteration cost applied large-scale VIs with certain structure. Numerical experiments have been conducted demonstrate potential advantages proposed algorithms. fact, all these algorithms are solve generalized whose is not necessarily monotone. will discuss OE-based policy evaluation methods reinforcement learning companion paper.
منابع مشابه
Operator-splitting Methods for General Mixed Variational Inequalities
In this paper, we use the technique of updating the solution to suggest and analyze a class of new splitting methods for solving general variational inequalities. It is shown that these modified methods converge for pseudomonotone operators, which is a weaker condition than monotonicity. Our method includes the two-step forward-backward splitting and extragradient methods for solving various cl...
متن کاملOperator-Splitting Methods for Monotone Affine Variational Inequalities, with a Parallel Application to Optimal Control
This paper applies splitting techniques developed for set-valued maximal monotone operators to monotone aane variational inequalities, including as a special case the classical linear comple-mentarity problem. We give a uniied presentation of several splitting algorithms for monotone operators, and then apply these results to obtain two classes of algorithms for aane variational inequalities. T...
متن کاملAdaptive Multilevel Monte Carlo Methods for Stochastic Variational Inequalities
While multilevel Monte Carlo (MLMC) methods for the numerical approximation of partial differential equations with uncertain coefficients enjoy great popularity, combinations with spatial adaptivity seem to be rare. We present an adaptive MLMC finite element approach based on deterministic adaptive mesh refinement for the arising ”pathwise” problems and outline a convergence theory in terms of ...
متن کاملVariational inequalities with operator solutions
The aim of the present paper is to give a new kind of point of view in the theory of variational inequalities. Our approach makes possible the study of both scalar and vector variational inequalities under a great variety of assumptions. One can include here the variational inequalities defined on reflexive or nonreflexive Banach spaces, as well as the vector variational inequalities defined on...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Siam Journal on Optimization
سال: 2022
ISSN: ['1095-7189', '1052-6234']
DOI: https://doi.org/10.1137/20m1381678