48 citations · 413 across the 59 of their papers we have counts for
8 papers · 1 filter
-Divergences: Interpolating between -Divergences and Integral Probability Metrics
Jeremiah Birrell, Paul Dupuis, Markos A. Katsoulakis +2
We develop a rigorous and general framework for constructing information-theoretic divergences that subsume both -divergences and integral probability metrics (IPMs), such as th…
Mutual Information for Explainable Deep Learning of Multiscale Systems
Søren Taverniers, Eric J. Hall, Markos A. Katsoulakis +1
Timely completion of design cycles for complex systems ranging from consumer electronics to hypersonic vehicles relies on rapid simulation-based prototyping. The latter typically i…
Uncertainty quantification for Markov Random Fields
Panagiota Birmpa, Markos A. Katsoulakis
We present an information-based uncertainty quantification method for general Markov Random Fields. Markov Random Fields (MRF) are structured, probabilistic graphical models over u…
Variational Representations and Neural Network Estimation of Rényi Divergences
Jeremiah Birrell, Paul Dupuis, Markos A. Katsoulakis +2
We derive a new variational formula for the Rényi family of divergences, , between probability measures and . Our result generalizes the classical Donsker-Varadha…
Data-driven Uncertainty Quantification for Systematic Coarse-grained Models
Tangxin Jin, Anthony Chazirakis, Evangelia Kalligiannaki +2
In this work, we present methodologies for the quantification of confidence in bottom-up coarse-grained models for molecular and macromolecular systems. Coarse-graining methods hav…
GINNs: Graph-Informed Neural Networks for Multiscale Physics
Eric J. Hall, Søren Taverniers, Markos A. Katsoulakis +1
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 fo…
Optimizing Variational Representations of Divergences and Accelerating their Statistical Estimation
Jeremiah Birrell, Markos A. Katsoulakis, Yannis Pantazis
Variational representations of divergences and distances between high-dimensional probability distributions offer significant theoretical insights and practical advantages in numer…
Cumulant GAN
Yannis Pantazis, Dipjyoti Paul, Michail Fasoulakis +2
In this paper, we propose a novel loss function for training Generative Adversarial Networks (GANs) aiming towards deeper theoretical understanding as well as improved stability an…