SS-ESOAP: Self-Scaled Adaptive Preconditioning for Physics-Informed Learning
Quick summary
arXiv:2608.29448v1 Announce Type: cross Abstract: Physics-informed neural networks (PINNs) often face ill-conditioned objectives that limit high-accuracy training. Dense quasi-Newton methods improve local conditioning but require expensive optimizer state, while Kronecker-factored methods such as SOAP scale to larger networks but rely on periodic basis updates. We introduce \method, which augments SOAP-style preconditioning with a scalar secant-energy correction adapted to Kronecker geometry and an adaptive basis update followed by variance-state downscaling. We characterize the directional se
Key takeaways
- arXiv:2608.29448v1 Announce Type: cross Abstract: Physics-informed neural networks (PINNs) often face ill-conditioned objectives that limit high-accuracy training.
- Dense quasi-Newton methods improve local conditioning but require expensive optimizer state, while Kronecker-factored methods such as SOAP scale to larger networks but rely on periodic basis updates.
- We introduce \method, which augments SOAP-style preconditioning with a scalar secant-energy correction adapted to Kronecker geometry and an adaptive basis update followed by variance-state downscaling.
Why it matters
“SS-ESOAP: Self-Scaled Adaptive Preconditioning for Physics-Informed Learning” is a product decision that may change how people work with AI. Its value depends on task completion, correction effort and data handling—not simply the presence of a new feature.
Member comments