activity
20162022
most citedLagrangian PINNs: A causality-conforming solution to failure modes of physics-informed neural networks

49 citations · 49 across the 2 of their papers we have counts for

collaborators

6 papers

cs.LG2022★ 49 cited

Lagrangian PINNs: A causality-conforming solution to failure modes of physics-informed neural networks

Rambod Mojgani, Maciej Balajewicz, Pedram Hassanzadeh

Physics-informed neural networks (PINNs) leverage neural-networks to find the solutions of partial differential equation (PDE)-constrained optimization problems with initial condit…

math.DS2020

Physics-aware registration based auto-encoder for convection dominated PDEs

Rambod Mojgani, Maciej Balajewicz

We design a physics-aware auto-encoder to specifically reduce the dimensionality of solutions arising from convection-dominated nonlinear physical systems. Although existing nonlin…

math.DS2018

Deep convolutional recurrent autoencoders for learning low-dimensional feature dynamics of fluid systems

Francisco J. Gonzalez, Maciej Balajewicz

Model reduction of high-dimensional dynamical systems alleviates computational burdens faced in various tasks from design optimization to model predictive control. One popular mode…

physics.flu-dyn2017

Transported snapshot model order reduction approach for parametric, steady-state fluid flows containing parameter dependent shocks

Nirmal J. Nair, Maciej Balajewicz

A new model order reduction approach is proposed for parametric steady-state nonlinear fluid flows characterized by shocks and discontinuities whose spatial locations and orientati…

physics.flu-dyn2017

Lagrangian basis method for dimensionality reduction of convection dominated nonlinear flows

Rambod Mojgani, Maciej Balajewicz

Foundations of a new projection-based model reduction approach for convection dominated nonlinear fluid flows are summarized. In this method the evolution of the flow is approximat…

cs.CE2016

Reduced Order Models for Pricing European and American Options under Stochastic Volatility and Jump-Diffusion Models

Maciej Balajewicz, Jari Toivanen

European options can be priced by solving parabolic partial(-integro) differential equations under stochastic volatility and jump-diffusion models like Heston, Merton, and Bates mo…