Skip to main content
Skip header

Christa Cuchiero

Title of the speech: Dynamic universal approximation and optimal control for non-Markovian systems via signature stochastic differential equations

Abstract:

Many applications in generative time series modeling, particularly in finance, require stochastic dynamics that are genuinely path-dependent and non-Markovian. Classical Markovian state-space models are often too restrictive to capture memory effects, delayed responses, volatility feedback, and other features generated by the past trajectory of the system. From a numerical perspective, the most natural route is to lift path dependence to an enlarged state space, thereby obtaining a Markovian approximation of the original dynamics. Among such lifts, signature stochastic differential equations (SDEs) provide a canonical and model-agnostic choice, building on the strong algebraic and approximation-theoretic properties of path signatures, which form a universal and non-parametric feature set for paths. We explain how this leads to dynamic universal approximation results for generic non-Markovian SDEs. We also show how the resulting finite-dimensional signature SDEs can be used in optimal control problems with path-dependent dynamics and objectives, reducing, for instance, the infinite-dimensional Hamilton-Jacobi-Bellman PDE to a much simpler Riccati ODE.

Bio:

Christa Cuchiero is a full professor at the University of Vienna. She earned her doctorate in Mathematics from ETH Zurich in 2011. Her research centers around mathematical finance, stochastic analysis, quantitative risk management and machine learning. She is particularly interested in classes of universal stochastic processes with applications in volatility modeling and portfolio theory, approximation theory in dynamic situations, data-driven risk inference and machine learning in finance. Christa Cuchiero has received several prizes and fellowships, including the prestigious START award of the Austrian Science Fund (FWF). She has given a number of keynote speeches and serves on the editorial board of several academic journals. She has also co-organized international conferences and a world online seminar series on machine learning in finance.