# Mathematical Foundations of Distributionally Robust Multistage Optimization

arXiv: https://arxiv.org/abs/2101.02498 · HTML: https://mlsanity.com/paper/2101.02498/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Jan 2021.

## Built on by (most cited first, 3 of 3)

- [Sinkhorn Distributionally Robust Optimization](https://mlsanity.com/paper/2109.11926/) (2021)
- [On the Foundation of Distributionally Robust Reinforcement Learning](https://mlsanity.com/paper/2311.09018/) (2023)
- [Numerical Methods for Convex Multistage Stochastic Optimization](https://mlsanity.com/paper/2303.15672/) (2023)

## Abstract (arXiv)

Distributionally robust optimization involves various probability measures in its problem formulation. They can be bundled to constitute a risk functional. For this equivalence, risk functionals constitute a fundamental building block in distributionally robust stochastic programming. Multistage programming requires conditional versions of risk functionals to re-assess future risk after partial realizations and after preceding decisions. This paper discusses a construction of the conditional counterpart of a risk functional by passing its genuine characteristics to its conditional counterparts. The conditional risk functionals turn out to be different from the nested analogues of the original (law invariant) risk measure. It is demonstrated that the initial measure and its nested decomposition can be used in a distributionally robust multistage setting.