Results 11 to 20 of about 108,723 (292)
Stochastic Approximations and Differential Inclusions; Part II: Applications [PDF]
We apply the theoretical results on ``stochastic approximations and differential inclusions'' developed in Benaïm Hofbauer and Sorin (2003) to several adaptive processes used in game theory including: classical and generalized approachability, no-regrets
Benaïm, Michel +2 more
core +6 more sources
Asynchronous stochastic approximation with differential inclusions [PDF]
The asymptotic pseudo-trajectory approach to stochastic approximation of Benaïm, Hofbauer and Sorin is extended for asynchronous stochastic approximations with a set-valued mean field.
David S. Leslie, Steven Perkins
doaj +6 more sources
Stochastic differential inclusions with Hilfer fractional derivative
In this paper, we study the existence of mild solutions of Hilfer fractional stochastic differential inclusions driven by sub fractional Brownian motion in the cases when the multivalued map is convex and non convex.
Meryem Chaouche, Toufik Guendouzi
semanticscholar +2 more sources
Stochastic approximation with discontinuous dynamics, differential inclusions, and applications
This work develops new results for stochastic approximation algorithms. The emphases are on treating algorithms and limits with discontinuities. The main ingredients include the use of differential inclusions, set-valued analysis, and non-smooth analysis, and stochastic differential inclusions. Under broad conditions, it is shown that a suitably scaled
Nguyen, Nhu, Yin, George
openaire +2 more sources
Smale Strategies for Network Prisoner's Dilemma Games [PDF]
Smale's approach \cite{Smale80} to the classical two-players repeated Prisoner's Dilemma game is revisited here for $N$-players and Network games in the framework of Blackwell's approachability, stochastic approximations and differential ...
Behrstock, Kashi +2 more
core +3 more sources
Stochastic Langevin Differential Inclusions with Applications to Machine Learning
Stochastic differential equations of Langevin-diffusion form have received significant attention, thanks to their foundational role in both Bayesian sampling algorithms and optimization in machine learning. In the latter, they serve as a conceptual model of the stochastic gradient flow in training over-parameterized models.
Fabio V. Difonzo +2 more
openaire +2 more sources
Fractional calculus is now used to accurately depict a range of real occurrences because it can explain the “long-tail memory” phenomena that have been seen through empirical research. Standard differential equations with integer order derivatives cannot
Yong-Ki Ma +7 more
doaj +1 more source
Background. E. Nelson [1-3] introduced derivatives on the average in the works and over time, they began to be studied as a separate class of stochastic differential equations.
O.O. Zheltikova
doaj +1 more source
THE BOUNDEDNESS OF SOLUTIONS FOR STOCHASTIC DIFFERENTIAL INCLUSIONS [PDF]
Let \((\Omega,{\mathcal F},P)\) be a complete probability with a right-continuous increasing family \(({\mathcal F_t})_{t\geq 0}\) of \(\sigma\)-fields each containing all \(P\)-nul sets. Let \(B= (B_t)_{t\geq 0}\) be an \(r\)-dimensional \(({\mathcal F}_t)\)-Brownian motion.
openaire +1 more source
On the Relationship Between Solutions of Stochastic and Random Differential Inclusions [PDF]
Some results on the relationship of the solutions of a stochastic di erential inclusion and the corresponding random di erential inclusion obtained after a change of variable are proved. As a consequence, we obtain the pullback convergence of the solutions of the stochastic inclusion to a compact random set.
Caraballo Garrido, Tomás +2 more
openaire +2 more sources

