3 papers
stat.ML2024
Score-based generative models are provably robust: an uncertainty quantification perspective
Nikiforos Mimikos-Stamatopoulos, Benjamin J. Zhang, Markos A. Katsoulakis
Through an uncertainty quantification (UQ) perspective, we show that score-based generative models (SGMs) are provably robust to the multiple sources of error in practical implemen…
math.OC2023
Sharp convergence rates for mean field control in the region of strong regularity
Pierre Cardaliaguet, Joe Jackson, Nikiforos Mimikos-Stamatopoulos +1
We study the convergence problem for mean field control, also known as optimal control of McKean-Vlasov dynamics. We assume that the data is smooth but not convex, and thus the lim…
math.AP2023
A Mean Field Game approach to Large Deviations for empirical measures under common noise
Nikiforos Mimikos-Stamatopoulos
We present a Mean Field Game approach to obtain the rate function for the empirical measure of interacting particles under McKean-Vlasov dynamics. Although the result is well known…