Convergence of Recursive Stochastic Algorithms Using Wasserstein Divergence
نویسندگان
چکیده
Related DatabasesWeb of Science You must be logged in with an active subscription to view this.Article DataHistorySubmitted: 4 January 2021Accepted: 01 July 2021Published online: 21 October 2021Keywordsiterative random maps, Wasserstein divergence, stochastic gradient descentAMS Subject Headings93E35, 60J20, 68Q32Publication DataISSN (online): 2577-0187Publisher: Society for Industrial and Applied MathematicsCODEN: sjmdaq
منابع مشابه
Stochastic Wasserstein Barycenters
We present a stochastic algorithm to compute the barycenter of a set of probability distributions under the Wasserstein metric from optimal transport. Unlike previous approaches, our method extends to continuous input distributions and allows the support of the barycenter to be adjusted in each iteration. We tackle the problem without regularization, allowing us to recover a sharp output whose ...
متن کاملthe investigation of research articles in applied linguistics: convergence and divergence in iranian elt context
چکیده ندارد.
Convergence of Stochastic Iterative Dynamic Programming Algorithms
Increasing attention has recently been paid to algorithms based on dynamic programming (DP) due to the suitability of DP for learning problems involving control. In stochastic environments where the system being controlled is only incompletely known, however, a unifying theoretical account of these methods has been missing. In this paper we relate DP-based learning algorithms to the powerful te...
متن کاملConvergence Analysis of Gradient Descent Stochastic Algorithms
This paper proves convergence of a sample-path based stochastic gradient-descent algorithm for optimizing expected-value performance measures in discrete event systems. The algorithm uses increasing precision at successive iterations, and it moves against the direction of a generalized gradient of the computed sample performance function. Two convergence results are established: one, for the ca...
متن کاملConvergence analysis of instrumental variable recursive subspace identification algorithms
The convergence properties of a recently developed recursive subspace identification algorithm are investigated in this paper. The algorithm operates on the basis of an extended instrumental variable (EIV) version of the propagator method for signal subspace estimation. It is proved that, under weak conditions on the input signal and the identified system, the considered MOESP class of recursiv...
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 mathematics of data science
سال: 2021
ISSN: ['2577-0187']
DOI: https://doi.org/10.1137/21m1389808