activity
20182020
most citedOvercoming the curse of dimensionality in the numerical approximation of high-dimensional semilinear elliptic partial differential equations

30 citations · 50 across the 4 of their papers we have counts for

collaborators

5 papers

math.NA2020

Weak error analysis for stochastic gradient descent optimization algorithms

Aritz Bercher, Lukas Gonon, Arnulf Jentzen +1

Stochastic gradient descent (SGD) type optimization schemes are fundamental ingredients in a large number of machine learning based algorithms. In particular, SGD type optimization…

math.PR202030 cited

Overcoming the curse of dimensionality in the numerical approximation of high-dimensional semilinear elliptic partial differential equations

Christian Beck, Lukas Gonon, Arnulf Jentzen

Recently, so-called full-history recursive multilevel Picard (MLP) approximation schemes have been introduced and shown to overcome the curse of dimensionality in the numerical app…

cs.LG201920 cited

Risk bounds for reservoir computing

Lukas Gonon, Lyudmila Grigoryeva, Juan-Pablo Ortega

We analyze the practices of reservoir computing in the framework of statistical learning theory. In particular, we derive finite sample upper bounds for the generalization error co…

q-fin.MF2019

Asset Pricing with General Transaction Costs: Theory and Numerics

Lukas Gonon, Johannes Muhle-Karbe, Xiaofei Shi

We study risk-sharing equilibria with general convex costs on the agents' trading rates. For an infinite-horizon model with linear state dynamics and exogenous volatilities, we pro…

math.PR2018

Linearized Filtering of Affine Processes Using Stochastic Riccati Equations

Lukas Gonon, Josef Teichmann

We consider an affine process which is only observed up to an additive white noise, and we ask for its law, for some time , conditional on all observations up to this t…