2 citations · 2 across the 4 of their papers we have counts for
17 papers
Small Models, Strong Priors: Architectural Inductive Bias for Parameter-Efficient Neural PDE Solvers
Shyam Sankaran, Hanwen Wang, Paris Perdikaris
Neural PDE solvers have followed the scaling trajectory of vision and language, with recent foundation models reaching billions of parameters. We argue that scale is a poor substit…
A Mutual Information Lower Bound for Multimodal Regression Active Learning
Leonardo Ferreira Guilhoto, Akshat Kaushal, Paris Perdikaris
Active learning for continuous regression has lacked an acquisition function that targets epistemic uncertainty when the predictive distribution is multimodal: variance misses moda…
Deep Learning Alternatives of the Kolmogorov Superposition Theorem
Leonardo Ferreira Guilhoto, Paris Perdikaris
This paper explores alternative formulations of the Kolmogorov Superposition Theorem (KST) as a foundation for neural network design. The original KST formulation, while mathematic…
When PINNs Go Wrong: Pseudo-Time Stepping Against Spurious Solutions
Sifan Wang, Shawn Koohy, Yiping Lu +1
Physics-informed neural networks (PINNs) provide a promising machine learning framework for solving partial differential equations, but their training often breaks down on challeng…
Self-Flow-Matching assisted Full Waveform Inversion
Xinquan Huang, Paris Perdikaris
Full-waveform inversion (FWI) is a high-resolution seismic imaging method that estimates subsurface velocity by matching simulated and recorded waveforms. However, FWI is highly no…
Multimodal Scientific Learning Beyond Diffusions and Flows
Leonardo Ferreira Guilhoto, Akshat Kaushal, Paris Perdikaris
Scientific machine learning (SciML) increasingly requires models that capture multimodal conditional uncertainty arising from ill-posed inverse problems, multistability, and chaoti…