7 citations · 19 across the 15 of their papers we have counts for
17 papers
Risk-Averse Control of Markov Systems with Value Function Learning
Andrzej Ruszczynski, Shangzhe Yang
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 approximate…
Distributionally Robust Learning with Weakly Convex Losses: Convergence Rates and Finite-Sample Guarantees
Landi Zhu, Mert Gürbüzbalaban, Andrzej Ruszczyński
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--semidevi…
Risk Filtering and Risk-Averse Control of Markovian Systems Subject to Model Uncertainty
Tomasz R. Bielecki, Igor Cialenco, Andrzej Ruszczyński
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 observe…
A Stochastic Subgradient Method for Distributionally Robust Non-Convex Learning
Mert Gürbüzbalaban, Andrzej Ruszczyński, Landi Zhu
We consider a distributionally robust formulation of stochastic optimization problems arising in statistical learning, where robustness is with respect to uncertainty in the underl…
Subregular Recourse in Nonlinear Multistage Stochastic Optimization
Darinka Dentcheva, Andrzej Ruszczynski
We consider nonlinear multistage stochastic optimization problems in the spaces of integrable functions. We allow for nonlinear dynamics and general objective functionals, includin…
A Stochastic Subgradient Method for Nonsmooth Nonconvex Multi-Level Composition Optimization
Andrzej Ruszczynski
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 t…
Convergence of a Stochastic Subgradient Method with Averaging for Nonsmooth Nonconvex Constrained Optimization
Andrzej Ruszczynski
We prove convergence of a single time-scale stochastic subgradient method with subgradient averaging for constrained problems with a nonsmooth and nonconvex objective function havi…
A Single Time-Scale Stochastic Approximation Method for Nested Stochastic Optimization
Saeed Ghadimi, Andrzej Ruszczyński, Mengdi Wang
We study constrained nested stochastic optimization problems in which the objective function is a composition of two smooth functions whose exact values and derivatives are not ava…
Risk Forms: Representation, Disintegration, and Application to Partially Observable Two-Stage Systems
Darinka Dentcheva, Andrzej Ruszczynski
We introduce the concept of a risk form, which is a real functional of two arguments: a measurable function on a Polish space and a measure on that space. We generalize the duality…
Time-Consistent Risk Measures for Continuous-Time Markov Chains
Darinka Dentcheva, Andrzej Ruszczynski
We develop an approach to time-consistent risk evaluation of continuous-time processes in Markov systems. Our analysis is based on dual representation of coherent risk measures, di…
Rate of Convergence of the Bundle Method
Yu Du, Andrzej Ruszczynski
We prove that the bundle method for nonsmooth optimization achieves solution accuracy in at most iterations, if…
Selective Linearization For Multi-Block Convex Optimization
Yu Du, Xiaodong Lin, Andrzej Ruszczynski
We consider the problem of minimizing a sum of several convex non-smooth functions. We introduce a new algorithm called the selective linearization method, which iteratively linear…
Discrete-Time Approximation of Risk-Averse Control Problems for Diffusion Processes
Andrzej Ruszczynski, Jianing Yao
We consider optimal control problems for diffusion processes, where the objective functional is defined by a time-consistent dynamic risk measure. We focus on coherent risk measure…
Statistical Estimation of Composite Risk Functionals and Risk Optimization Problems
Darinka Dentcheva, Spiridon Penev, Andrzej Ruszczynski
We address the statistical estimation of composite functionals which may be nonlinear in the probability measure. Our study is motivated by the need to estimate coherent measures o…
Common Mathematical Foundations of Expected Utility and Dual Utility Theories
Darinka Dentcheva, Andrzej Ruszczynski
We show that the main results of the expected utility and dual utility theories can be derived in a unified way from two fundamental mathematical ideas: the separation principle of…
Risk-Averse Control of Undiscounted Transient Markov Models
Ozlem Cavus, Andrzej Ruszczynski
We use Markov risk measures to formulate a risk-averse version of the undiscounted total cost problem for a transient controlled Markov process. We derive risk-averse dynamic progr…
Alternating Linearization for Structured Regularization Problems
Xiaodong Lin, Minh Pham, Andrzej Ruszczynski
We adapt the alternating linearization method for proximal decomposition to structured regularization problems, in particular, to the generalized lasso problems. The method is rela…