Stochastic approximation algorithms with constant step size whose average is cooperative
نویسندگان
چکیده
منابع مشابه
Linear Stochastic Approximation: Constant Step-Size and Iterate Averaging
We consider d-dimensional linear stochastic approximation algorithms (LSAs) with a constant step-size and the so called Polyak-Ruppert (PR) averaging of iterates. LSAs are widely applied in machine learning and reinforcement learning (RL), where the aim is to compute an appropriate θ∗ ∈ R (that is an optimum or a fixed point) using noisy data and O(d) updates per iteration. In this paper, we ar...
متن کاملAsymptotic Properties of Two Time-Scale Stochastic Approximation Algorithms with Constant Step Sizes
Asymptotic properties of two time-scale stochastic approximation algorithms with constant step sizes are analyzed in this paper. The analysis is carried out for the algorithms with additive noise, as well as for the algorithms with non-additive noise. The algorithms with additive noise are considered for the case where the noise is state-dependent and admits the decomposition as a sum of a mart...
متن کاملStochastic Approximations with Constant Step Size and Differential Inclusions
We consider stochastic approximation processes with constant step size whose associated deterministic system is an upper semicontinous differential inclusion. We prove that over any finite time span, the sample paths of the stochastic process are closely approximated by a solution of the differential inclusion with high probability. We then analyze infinite horizon behavior, showing that if the...
متن کاملConvergence diagnostics for stochastic gradient descent with constant step size
Iterative procedures in stochastic optimization are typically comprised of a transient phase and a stationary phase. During the transient phase the procedure converges towards a region of interest, and during the stationary phase the procedure oscillates in a convergence region, commonly around a single point. In this paper, we develop a statistical diagnostic test to detect such phase transiti...
متن کاملA stochastic approximation algorithm with multiplicative step size adaptation
An algorithm of searching a zero of an unknown function φ : R → R is considered, xt = xt−1−γt−1yt, t = 1, 2, . . ., where yt = φ(xt−1)+ξt is the value of φmeasured at xt−1 with some error, ξt is this error. The step sizes γt > 0 are random positive values and are calculated according to the rule: γt = min{u γt−1, ḡ} if yt−1yt > 0, and γt = d γt−1, otherwise. Here 0 < d < 1 < u, ḡ > 0. The funct...
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: The Annals of Applied Probability
سال: 1999
ISSN: 1050-5164
DOI: 10.1214/aoap/1029962603