4 papers
Physics-Informed Neural Network Surrogate for Oxygen Vacancy Dynamics in epitaxial on Si memristors via Dynamic Spectral Optimization
Rodion Podorozhny, Nikoleta Theodoropoulou, Jelena Tešić
Physics-informed neural networks (PINNs) offer a promising framework for modeling semiconductor devices, yet standard architectures struggle with severe numerical stiffness and mul…
Blockwise Stabilized Adaptive Cubic Regularization with Subsolvers via Recurrence
Rodion Podorozhny
Cubic regularized Newton methods have the optimal global rate, but a dense subproblem solve limits the feasible block size. Scalable Cubic Newton variants r…
Loss Landscape Features That Make Adam Stall: Definitions, Estimators, and the Preconditioned Hessian View
Rodion Podorozhny
Across implicit-neural-representation (INR) architectures and analytic benchmarks we observe that a thoroughly tuned Adam (especially its learning rate (lr), e.g. in a hyperparamet…
Physics-Guided Transformer (PGT): Physics-Aware Attention Mechanism for PINNs
Ehsan Zeraatkar, Rodion Podorozhny, Jelena Tešić
Reconstructing continuous physical fields from sparse, irregular observations is a central challenge in scientific machine learning, particularly for systems governed by partial di…