no code implementations • 9 Feb 2024 • Benjamin J. Zhang, Siting Liu, Wuchen Li, Markos A. Katsoulakis, Stanley J. Osher
Via a Cole-Hopf transformation and taking advantage of the fact that the cross-entropy can be related to a linear functional of the density, we show that the HJB equation is an uncontrolled FP equation.
no code implementations • 22 May 2023 • Ziyu Chen, Markos A. Katsoulakis, Luc Rey-Bellet, Wei Zhu
Group-invariant generative adversarial networks (GANs) are a type of GANs in which the generators and discriminators are hardwired with group symmetries.
no code implementations • 26 Apr 2023 • Benjamin J. Zhang, Markos A. Katsoulakis
The mathematical structure described by the MFG optimality conditions identifies the inductive biases of generative flows.
no code implementations • 3 Feb 2023 • Ziyu Chen, Markos A. Katsoulakis, Luc Rey-Bellet, Wei Zhu
We rigorously quantify the improvement in the sample complexity of variational divergence estimations for group-invariant distributions.
1 code implementation • 31 Oct 2022 • Hyemin Gu, Panagiota Birmpa, Yannis Pantazis, Luc Rey-Bellet, Markos A. Katsoulakis
We build a new class of generative algorithms capable of efficiently learning an arbitrary target distribution from possibly scarce, high-dimensional data and subsequently generate new samples.
1 code implementation • 10 Oct 2022 • Jeremiah Birrell, Yannis Pantazis, Paul Dupuis, Markos A. Katsoulakis, Luc Rey-Bellet
We propose a new family of regularized R\'enyi divergences parametrized not only by the order $\alpha$ but also by a variational function space.
no code implementations • 2 Feb 2022 • Jeremiah Birrell, Markos A. Katsoulakis, Luc Rey-Bellet, Wei Zhu
Generative adversarial networks (GANs), a class of distribution-learning methods based on a two-player game between a generator and a discriminator, can generally be formulated as a minmax problem based on the variational representation of a divergence between the unknown and the generated distributions.
no code implementations • 29 Sep 2021 • Jeremiah Birrell, Markos A. Katsoulakis, Yannis Pantazis, Dipjyoti Paul, Anastasios Tsourtis
Unfortunately, the approximation of expectations that are inherent in variational formulas by statistical averages can be problematic due to high statistical variance, e. g., exponential for the Kullback-Leibler divergence and certain estimators.
no code implementations • 17 Jul 2021 • Panagiota Birmpa, Jinchao Feng, Markos A. Katsoulakis, Luc Rey-Bellet
Probabilistic graphical models are a fundamental tool in probabilistic modeling, machine learning and artificial intelligence.
no code implementations • 11 Nov 2020 • Jeremiah Birrell, Paul Dupuis, Markos A. Katsoulakis, Yannis Pantazis, Luc Rey-Bellet
We develop a rigorous and general framework for constructing information-theoretic divergences that subsume both $f$-divergences and integral probability metrics (IPMs), such as the $1$-Wasserstein distance.
no code implementations • 7 Sep 2020 • Søren Taverniers, Eric J. Hall, Markos A. Katsoulakis, Daniel M. Tartakovsky
Timely completion of design cycles for complex systems ranging from consumer electronics to hypersonic vehicles relies on rapid simulation-based prototyping.
no code implementations • 31 Aug 2020 • Panagiota Birmpa, Markos A. Katsoulakis
In the latter, we develop uncertainty quantification bounds for finite size effects and phase diagrams, which constitute two of the typical predictions goals of statistical mechanics modeling.
1 code implementation • 7 Jul 2020 • Jeremiah Birrell, Paul Dupuis, Markos A. Katsoulakis, Luc Rey-Bellet, Jie Wang
We further show that this R\'enyi variational formula holds over a range of function spaces; this leads to a formula for the optimizer under very weak assumptions and is also key in our development of a consistency theory for R\'enyi divergence estimators.
no code implementations • 26 Jun 2020 • Eric J. Hall, Søren Taverniers, Markos A. Katsoulakis, Daniel M. Tartakovsky
We introduce the concept of a Graph-Informed Neural Network (GINN), a hybrid approach combining deep learning with probabilistic graphical models (PGMs) that acts as a surrogate for physics-based representations of multiscale and multiphysics systems.
no code implementations • 15 Jun 2020 • Jeremiah Birrell, Markos A. Katsoulakis, Yannis Pantazis
Recently, they have gained popularity in machine learning as a tractable and scalable approach for training probabilistic models and for statistically differentiating between data distributions.
no code implementations • 6 Jan 2019 • Kimoon Um, Eric Joseph Hall, Markos A. Katsoulakis, Daniel M. Tartakovsky
The global sensitivity indices are used to rank the effect of uncertainty in microscopic parameters on macroscopic QoIs, to quantify the impact of causality on the multiscale model's predictions, and to provide physical interpretations of these results for hierarchical nanoporous materials.