Zobrazeno 1 - 10
of 297
pro vyhledávání: '"Ruszczyński, Andrzej"'
Autor:
Ruszczyński, Andrzej, Yang, Shangzhe
We consider stochastic optimization problems involving an expected value of a nonlinear function of a base random vector and a conditional expectation of another function depending on the base random vector, a dependent random vector, and the decisio
Externí odkaz:
http://arxiv.org/abs/2405.10815
Autor:
Lin, Zhengqi, Ruszczynski, Andrzej
A generalization of the Wasserstein metric, the integrated transportation distance, establishes a novel distance between probability kernels of Markov systems. This metric serves as the foundation for an efficient approximation technique, enabling th
Externí odkaz:
http://arxiv.org/abs/2312.01432
Autor:
Ruszczynski, Andrzej, Yang, Shangzhe
We consider a control problem for a finite-state Markov system whose performance is evaluated by a coherent Markov risk measure. For each policy, the risk of a state is approximated by a function of its features, thus leading to a lower-dimensional p
Externí odkaz:
http://arxiv.org/abs/2312.00946
Autor:
Lin, Zhengqi, Ruszczynski, Andrzej
We introduce a distance between kernels based on the Wasserstein distances between their values, study its properties, and prove that it is a metric on an appropriately defined space of kernels. We also relate it to various modes of convergence in th
Externí odkaz:
http://arxiv.org/abs/2311.06645
We consider a distributionally robust stochastic optimization problem and formulate it as a stochastic two-level composition optimization problem with the use of the mean--semideviation risk measure. In this setting, we consider a single time-scale a
Externí odkaz:
http://arxiv.org/abs/2301.06619
We consider a Markov decision process subject to model uncertainty in a Bayesian framework, where we assume that the state process is observed but its law is unknown to the observer. In addition, while the state process and the controls are observed
Externí odkaz:
http://arxiv.org/abs/2206.09235
We consider a distributionally robust formulation of stochastic optimization problems arising in statistical learning, where robustness is with respect to uncertainty in the underlying data distribution. Our formulation builds on risk-averse optimiza
Externí odkaz:
http://arxiv.org/abs/2006.04873
Autor:
Kose, Umit, Ruszczynski, Andrzej
We consider reinforcement learning with performance evaluated by a dynamic risk measure. We construct a projected risk-averse dynamic programming equation and study its properties. Then we propose risk-averse counterparts of the methods of temporal d
Externí odkaz:
http://arxiv.org/abs/2003.00780
Autor:
Ruszczynski, Andrzej
We propose a single time-scale stochastic subgradient method for constrained optimization of a composition of several nonsmooth and nonconvex functions. The functions are assumed to be locally Lipschitz and differentiable in a generalized sense. Only
Externí odkaz:
http://arxiv.org/abs/2001.10669