Siddhartha Mishra

Siddhartha Mishra

Auto-generated profile, based on publicly available information

Siddhartha Mishra

ETH Zurich

Research Focus & Metrics

Academic Career Length

18Years (2009-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
17 June 2021 in IMA Journal of Numerical Analysis
Verified
Journal Article
Closed access
PDF file
SMSiddhartha Mishra
Siddhartha Mishra
RMRoberto Molinaro
Roberto Molinaro
Physics-informed neural networks (PINNs) have recently been very successfully applied for efficiently approximating inverse problems for partial differential equations (PDEs). We focus on a particular class of inverse problems, the so-called data assimilation or unique continuation problems, and prove rigorous estimates on the generalization error of PINNs approximating them. An abstract framework is presented and conditional stability estimates for the underlying inverse problem are employed to derive the estimate on the PINN generalization error, providing rigorous justification for the use of PINNs in this context. The abstract framework is illustrated with examples of four prototypical linear PDEs. Numerical experiments, validating the proposed theory, are also presented.

14 January 2022 in IMA Journal of Numerical Analysis
Verified
Journal Article
Open access
PDF file
SMSiddhartha Mishra
Siddhartha Mishra
RMRoberto Molinaro
Roberto Molinaro
Physics-informed neural networks (PINNs) have recently been widely used for robust and accurate approximation of partial differential equations (PDEs). We provide upper bounds on the generalization error of PINNs approximating solutions of the forward problem for PDEs. An abstract formalism is introduced and stability properties of the underlying PDE are leveraged to derive an estimate for the generalization error in terms of the training error and number of training samples. This abstract framework is illustrated with several examples of nonlinear PDEs. Numerical experiments, validating the proposed theory, are also presented.

1 January 2022 in Transactions of Mathematics and Its Applications
Verified
Journal Article
Open access
PDF file
SLSamuel Lanthaler
Samuel Lanthaler
SMSiddhartha Mishra
Siddhartha Mishra
GKGeorge E Karniadakis
George E Karniadakis
DeepONets have recently been proposed as a framework for learning nonlinear operators mapping between infinite-dimensional Banach spaces. We analyze DeepONets and prove estimates on the resulting approximation and generalization errors. In particular, we extend the universal approximation property of DeepONets to include measurable mappings in non-compact spaces. By a decomposition of the error into encoding, approximation and reconstruction errors, we prove both lower and upper bounds on the total error, relating it to the spectral decay properties of the covariance operators, associated with the underlying measures. We derive almost optimal error bounds with very general affine reconstructors and with random sensor locations as well as bounds on the generalization error, using covering number arguments. We illustrate our general framework with four prototypical examples of nonlinear operators, namely those arising in a nonlinear forced ordinary differential equation, an elliptic partial differential equation (PDE) with variable coefficients and nonlinear parabolic and hyperbolic PDEs. While the approximation of arbitrary Lipschitz operators by DeepONets to accuracy |$\epsilon $| is argued to suffer from a ‘curse of dimensionality’ (requiring a neural networks of exponential size in |$1/\epsilon $|⁠), in contrast, for all the above concrete examples of interest, we rigorously prove that DeepONets can break this curse of dimensionality (achieving accuracy |$\epsilon $| with neural networks of size that can grow algebraically in |$1/\epsilon $|⁠).Thus, we demonstrate the efficient approximation of a potentially large class of operators with this machine learning framework.

5 April 2012 in Mathematics of Computation
Verified
Journal Article
Open access
PDF file
SMS. Mishra
S. Mishra
CSCh. Schwab
Ch. Schwab
We consider scalar hyperbolic conservation laws in spatial dimension d ≥ 1 d\geq 1 with stochastic initial data. We prove existence and uniqueness of a random-entropy solution and give sufficient conditions on the initial data that ensure the existence of statistical moments of any order k k of this random entropy solution. We present a class of numerical schemes of multi-level Monte Carlo Finite Volume (MLMC-FVM) type for the approximation of the ensemble average of the random entropy solutions as well as of their k k -point space-time correlation functions. These schemes are shown to obey the same accuracy vs. work estimate as a single application of the finite volume solver for the corresponding deterministic problem. Numerical experiments demonstrating the efficiency of these schemes are presented. In certain cases, statistical moments of discontinuous solutions are found to be more regular than pathwise solutions.

15 November 2022 in Advances in Computational Mathematics
Verified
Journal Article
Open access
PDF file
TRTim De Ryck
Tim De Ryck
SMSiddhartha Mishra
Siddhartha Mishra
Physics-informed neural networks approximate solutions of PDEs by minimizing pointwise residuals. We derive rigorous bounds on the error, incurred by PINNs in approximating the solutions of a large class of linear parabolic PDEs, namely Kolmogorov equations that include the heat equation and Black-Scholes equation of option pricing, as examples. We construct neural networks, whose PINN residual (generalization error) can be made as small as desired. We also prove that the total L2-error can be bounded by the generalization error, which in turn is bounded in terms of the training error, provided that a sufficient number of randomly chosen training (collocation) points is used. Moreover, we prove that the size of the PINNs and the number of training samples only grow polynomially with the underlying dimension, enabling PINNs to overcome the curse of dimensionality in this context. These results enable us to provide a comprehensive error analysis for PINNs in approximating Kolmogorov PDEs.