no code implementations • 12 Feb 2024 • Razvan-Andrei Lascu, Mateusz B. Majka, Łukasz Szpruch
We study two variants of the mirror descent-ascent algorithm for solving min-max problems on the space of measures: simultaneous and sequential.
no code implementations • 10 Feb 2024 • Gholamali Aminian, Yixuan He, Gesine Reinert, Łukasz Szpruch, Samuel N. Cohen
This work provides a theoretical framework for assessing the generalization error of graph classification tasks via graph neural networks in the over-parameterized regime, where the number of parameters surpasses the quantity of data points.
no code implementations • 20 Jun 2023 • Gholamali Aminian, Samuel N. Cohen, Łukasz Szpruch
We propose a novel framework for exploring weak and $L_2$ generalization errors of algorithms through the lens of differential calculus on the space of probability measures.
1 code implementation • 8 Feb 2023 • samuel cohen, Marc Sabaté Vidales, David Šiška, Łukasz Szpruch
We investigate whether the fee income from trades on the CFM is sufficient for the liquidity providers to hedge away the exposure to market risk.
no code implementations • 10 Jun 2020 • David Šiška, Łukasz Szpruch
This paper studies stochastic control problems with the action space taken to be probability measures, with the objective penalised by the relative entropy.
1 code implementation • 10 Jun 2020 • Mateusz B. Majka, Marc Sabate-Vidales, Łukasz Szpruch
In this paper, we construct a Multi-index Antithetic Stochastic Gradient Algorithm (MASGA) whose implementation is independent of the structure of the target measure and which achieves performance on par with Monte Carlo estimators that have access to unbiased samples from the distribution of interest.
no code implementations • 11 Dec 2019 • Jean-François Jabir, David Šiška, Łukasz Szpruch
We develop a framework for the analysis of deep neural networks and neural ODE models that are trained with stochastic gradient algorithms.