REVIEW 3 cited by
Multilevel Picard approximations for high-dimensional semilinear second-order PDEs with Lipschitz nonlinearities
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
abstract
The recently introduced full-history recursive multilevel Picard (MLP) approximation methods have turned out to be quite successful in the numerical approximation of solutions of high-dimensional nonlinear PDEs. In particular, there are mathematical convergence results in the literature which prove that MLP approximation methods do overcome the curse of dimensionality in the numerical approximation of nonlinear second-order PDEs in the sense that the number of computational operations of the proposed MLP approximation method grows at most polynomially in both the reciprocal $1/\epsilon$ of the prescribed approximation accuracy $\epsilon>0$ and the PDE dimension $d\in \mathbb{N}=\{1,2,3, \ldots\}$. However, in each of the convergence results for MLP approximation methods in the literature it is assumed that the coefficient functions in front of the second-order differential operator are affine linear. In particular, until today there is no result in the scientific literature which proves that any semilinear second-order PDE with a general time horizon and a non affine linear coefficient function in front of the second-order differential operator can be approximated without the curse of dimensionality. It is the key contribution of this article to overcome this obstacle and to propose and analyze a new type of MLP approximation method for semilinear second-order PDEs with possibly nonlinear coefficient functions in front of the second-order differential operators. In particular, the main result of this article proves that this new MLP approximation method does indeed overcome the curse of dimensionality in the numerical approximation of semilinear second-order PDEs.
Forward citations
Cited by 3 Pith papers
-
Full history recursive multilevel Picard approximations suffer from the curse of dimensionality for the Hamilton-Jacobi-Bellman equation of a stochastic control problem
For a simple HJB control example, MLP approximations have L2 error growing like d^{n/2}/(c^n sqrt(n!)) - 1, so no polynomial-in-dimension error bound can hold uniformly as the number of levels grows.
-
Deep neural networks can provably solve Bellman equations for Markov decision processes without the curse of dimensionality
Q-functions of infinite-horizon discounted MDPs with finite action sets are approximable by leaky ReLU networks with polynomially growing parameter counts, provided rewards and transitions are themselves DNN-approximable.
-
Multilevel Picard approximations for McKean-Vlasov stochastic differential equations with nonconstant diffusion
An MLP algorithm that stores entire solution paths approximates distribution-dependent SDEs with nonconstant diffusion in L2 with cost polynomial in dimension and inverse tolerance.
Discussion (0). Continue with ORCID to comment.