Author

Irina Tezaur

5 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Sep 2026

Learning Long-Term Stable Operator Inference Reduced-Order Models of Fluid Flows through Online Spatial Filtering

This paper introduces an online evolve--filter--relax (EFR) strategy for long-term stability of Operator Inference (OpInf) reduced-order models (ROMs) of complex fluid flow simulations that uses spatial filtering inspired from large eddy simulation to significantly improve long-term stability and predictive performance...

Ian Moore, Ping-Hsuan Tsai, Anthony Gruber et al. · 1 citation

Adaptive Hybrid Modeling via Schwarz Alternating Coupling and Operator Inference Reduced Order Models

A novel domain decomposition-based approach for creating adaptive hybrid models with the help of the Schwarz alternating method and some recent extensions of SAM are presented to enable the overlapping and non-overlapping coupling of non-intrusive polynomial and neural network-(NN-)based Operator Inference (OpInf) ROMs...

Irina Tezaur, Eric J. Parish, Anthony Gruber et al. · 0 citations

#machine learning Preprint Sep 2026

Hybrid coupling with numerics-informed neural networks and the overlapping Schwarz alternating method

A hybrid modeling framework for coupling pre-trained numerics-informed neural networks (NINNs) with classical full order models (FOMs) using the overlapping Schwarz alternating method, and the resulting hybrid NINN-FOM solutions agree closely with the corresponding FOM-FOM Schwarz solutions.

George Chumbipuma, Irina Tezaur, Alejandro N. Diaz et al. · 0 citations

#artificial intelligence Preprint Sep 2026

Adaptive hybrid coupling with operator inference, the overlapping Schwarz alternating method and reinforcement learning

This work introduces a reinforcement learning (RL)-based approach for online adaptation of FOM-ROM models coupled via the overlapping Schwarz alternating method (O-SAM), an iterative domain decomposition method that solves subdomain-local problems while exchanging solution information through transmission boundary cond...

Trishit Mondal, Irina Tezaur, Anthony Gruber · 0 citations

#machine learning Preprint Sep 2026

Tackling Failure Modes of PINNs and PIKANs Using Conflict-Free Gradients

Norm-PCGrad is proposed, a normalized variant that achieves state-of-the-art accuracy across a range of 2D and 3D domain decomposition problems and demonstrates that gradient surgery extends to physics-informed Kolmogorov-Arnold Networks, yielding substantial accuracy improvements for 3D domain decomposition.

S. S. Menon, Irina Tezaur, Ameya D. Jagtap · 2 citations