BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CREST - ECPv5.1.3//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:CREST
X-ORIGINAL-URL:https://crest.science
X-WR-CALDESC:Events for CREST
BEGIN:VTIMEZONE
TZID:Europe/Helsinki
BEGIN:DAYLIGHT
TZOFFSETFROM:+0200
TZOFFSETTO:+0300
TZNAME:EEST
DTSTART:20260329T010000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0300
TZOFFSETTO:+0200
TZNAME:EET
DTSTART:20261025T010000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=Europe/Helsinki:20261015T110000
DTEND;TZID=Europe/Helsinki:20261015T120000
DTSTAMP:20260916T081322
CREATED:20260915T092106Z
LAST-MODIFIED:20260915T092106Z
UID:19137-1792062000-1792065600@crest.science
SUMMARY:Carlos ESTEVE-YAGUE (Universidad de Alicante) "Solving Hamilton-Jacobi-Bellman Equations with Neural Networks: Monotone Discretizations and Dimension-Robust Convergence"
DESCRIPTION:[vc_row][vc_column][vc_column_text]Séminaire Mathématiques Financières \nJeudi 15 octobre 2026 \n11h – 12h \n  \nSalle 3001 \nCarlos ESTEVE-YAGUE (Universidad de Alicante) “Solving Hamilton-Jacobi-Bellman Equations with Neural Networks: Monotone Discretizations and Dimension-Robust Convergence” \nSummary: \nIn recent years\, advancements in deep learning and new optimization algorithms have motivated the use of artificial neural networks to solve non-linear problems in high-dimensional setups. A relevant case of application is the approximation of the value function for optimal control problems\, which can be characterized by the viscosity solution of the associated Hamilton-Jacobi-Bellman (HJB) equation. Along with the neural network architecture\, one of the crucial steps in implementing any deep learning method is the choice of the loss functional used to train the network parameters\, typically through gradient-based optimization. This talk takes up exactly that question for HJB equations: which loss functional design guarantees convergence to the viscosity solution\, and at what rate? I will show that using a monotone discretization of the underlying differential operator ensures the associated loss functional has a unique critical point\, which approximates the viscosity solution. Moreover\, for sufficiently coarse discretizations\, we prove a dimension-robust Polyak–Łojasiewicz inequality. \nThis implies linear convergence of the associated gradient flow at a rate that avoids the curse of dimensionality. Building on this theoretical foundation\, we propose a multi-level training algorithm that exploits the faster convergence available on the coarser grids of the discretization. \nJoint work: Olivier BOKANOWSKI\, Richard TSAI[/vc_column_text][/vc_column][/vc_row]\n
URL:https://crest.science/event/carlos-esteve-yague-universidad-de-alicante-solving-hamilton-jacobi-bellman-equations-with-neural-networks-monotone-discretizations-and-dimension-robust-convergence/
LOCATION:3001
CATEGORIES:Finance-Insurance,Mathematical Finance
END:VEVENT
END:VCALENDAR