no code implementations • 24 Jul 2024 • Pierre-Cyril Aubin-Frankowski, Yohann de Castro, Axel Parmentier, Alessandro Rudi
Such approaches train policies that chain a statistical model with a surrogate combinatorial optimization oracle to map any instance of the problem to a feasible solution.
1 code implementation • 13 Jun 2024 • Clément Bonet, Théo Uscidda, Adam David, Pierre-Cyril Aubin-Frankowski, Anna Korba
As the problem of minimizing functionals on the Wasserstein space encompasses many applications in machine learning, different optimization algorithms on $\mathbb{R}^d$ have received their counterpart analog on the Wasserstein space.
no code implementations • 16 Jan 2023 • Pierre-Cyril Aubin-Frankowski, Alessandro Rudi
Assuming further that the functions appearing in the problem are smooth, focusing on pointwise equality constraints enables the use of scattering inequalities to mitigate the curse of dimensionality in sampling the constraints.
no code implementations • 17 Jun 2022 • Pierre-Cyril Aubin-Frankowski, Anna Korba, Flavien Léger
We also show that Expectation Maximization (EM) can always formally be written as a mirror descent.
2 code implementations • 20 May 2021 • Anna Korba, Pierre-Cyril Aubin-Frankowski, Szymon Majewski, Pierre Ablin
We investigate the properties of its Wasserstein gradient flow to approximate a target probability distribution $\pi$ on $\mathbb{R}^d$, known up to a normalization constant.
no code implementations • 5 Jan 2021 • Pierre-Cyril Aubin-Frankowski, Zoltan Szabo
The modular nature of the proposed approach allows to simultaneously handle multiple shape constraints, and to tighten an infinite number of constraints into finitely many.
1 code implementation • NeurIPS 2020 • Pierre-Cyril Aubin-Frankowski, Zoltan Szabo
Shape constraints (such as non-negativity, monotonicity, convexity) play a central role in a large number of applications, as they usually improve performance for small sample size and help interpretability.