135 citations · 666 across the 42 of their papers we have counts for
7 papers · 1 filter
INEUS: Iterative Neural Solver for High-Dimensional PIDEs
Jean-Loup Dupret, Davide Gallon, Patrick Cheridito
In this paper, we introduce INEUS, a meshfree iterative neural solver for partial integro-differential equations (PIDEs). The method replaces the explicit evaluation of nonlocal ju…
Physics-informed diffusion models in spectral space
Davide Gallon, Philippe von Wurstemberger, Patrick Cheridito +1
We propose physics-informed spectral diffusion (PISD), a methodology that combines generative latent diffusion models with physics-informed machine learning to generate solutions o…
Deep Legendre Transform
Aleksey Minabutdinov, Patrick Cheridito
We introduce a novel deep learning algorithm for computing convex conjugates of differentiable convex functions, a fundamental operation in convex analysis with various application…
Deep Learning for Continuous-Time Stochastic Control with Jumps
Patrick Cheridito, Jean-Loup Dupret, Donatien Hainaut
In this paper, we introduce a model-based deep-learning approach to solve finite-horizon continuous-time stochastic control problems with jumps. We iteratively train two neural net…
Gradient descent provably escapes saddle points in the training of shallow ReLU networks
Patrick Cheridito, Arnulf Jentzen, Florian Rossmannek
Dynamical systems theory has recently been applied in optimization to prove that gradient descent algorithms bypass so-called strict saddle points of the loss function. However, in…
Landscape analysis for shallow neural networks: complete classification of critical points for affine target functions
Patrick Cheridito, Arnulf Jentzen, Florian Rossmannek
In this paper, we analyze the landscape of the true loss of neural networks with one hidden layer and ReLU, leaky ReLU, or quadratic activation. In all three cases, we provide a co…