Skip to main content
Learning with Stochastic Orders
Add to Calendar 2022-09-22T19:30:00 2022-09-22T20:30:00 UTC Learning with Stochastic Orders 201 Thomas Building, University Park, PA
Start DateThu, Sep 22, 2022
3:30 PM
End DateThu, Sep 22, 2022
4:30 PM
Presented By
Youssef Mroueh (IBM Research)
Event Series: Statistics Colloquia

Learning high-dimensional distributions is often done with explicit likelihood modeling or implicit modeling via minimizing integral probability metrics (IPMs). In this paper, we expand this learning paradigm to stochastic orders, namely, the convex or Choquet order between probability measures. Towards this end, we introduce the Choquet-Toland distance between probability measures, that can be used as a drop-in replacement for IPMs. We also introduce the Variational Dominance Criterion (VDC) to learn probability measures with dominance constraints, that encode the desired stochastic order between the learned measure and a known baseline. We analyze both quantities and show that they suffer from the curse of dimensionality and propose surrogates via input convex maxout networks (ICMNs), that enjoy parametric rates. Finally, we provide a min-max framework for learning with stochastic orders and validate it experimentally on synthetic and high-dimensional image generation, with promising results. The code is available at

Joint work with Carles Domingo Enrich and Yair Schiff