Speaker: Luca Galimberti (King's College London)

Title: Deep Learning methods for Limit Order Books: an Infinite-Dimensional Perspective

Abstract: Moving from the optimal liquidation problems proposed by Abi Jaber and Neuman (2024), we study operator learning in the context of linear propagator models with transient price impact à la Bouchaud et al. (2004) and Gatheral (2010). Transient price impact persists and decays over time according to some square integrable propagator kernel H.

More specifically, we show that the optimal execution strategy u = u(H) depends continuously on H, therefore giving rise to a highly non-linear continuous solution operator S between suitable infinite-dimensional Banach spaces. In view of an appropriate infinite-dimensional Universal Approximation Theorem, this operator S can in turn be approximated via ad hoc neural architectures, offering a quick to evaluate surrogate of the operator S in rapidly varying market conditions.

Time and place: April 22, 2026, 11:00 – 12:00, University of Oslo, NHA Room 723.

Please see the full announcement for information about speakers, logistics and registration (the event is hybrid - please register for the mailing list to get the Zoom link).

This series of webinars addresses all interested people in probability, stochastic analysis, control, risk evaluation, statistics, with a view towards applications, in particular to finance, economy, energy markets and production, but also to physics and biology.