A Convex-Inspired Neural Construction for Structured and Generalizable Nonlinear Model Reduction
By: Shixun Huang, Eitan Grinspun, Yue Chang
Potential Business Impact:
Makes computer simulations of wobbly things stable.
Real-time simulation of deformable objects relies on model reduction to achieve interactive performance while maintaining physical fidelity. Traditional linear methods, such as principal component analysis (PCA), provide structured and predictable behavior thanks to their linear formulation, but are limited in expressiveness. Nonlinear model reduction, typically implemented with neural networks, offers richer representations and higher compression; however, without structural constraints, the learned mappings often fail to generalize beyond the training distribution, leading to unstable or implausible deformations. We present a symmetric, convex-inspired neural formulation that bridges the gap between linear and nonlinear model reduction. Our approach adopts an input-convex neural network (ICNN) augmented with symmetry constraints to impose structure on the nonlinear decoder. This design retains the flexibility of neural mappings while embedding physical consistency, yielding coherent and stable displacements even under unseen conditions. We evaluate our method on challenging deformation scenarios involving forces of different magnitudes, inverse directions, and sparsely sampled training data. Our approach demonstrates superior generalization while maintaining compact reduced spaces, and supports real-time interactive applications.
Similar Papers
Polyconvex Physics-Augmented Neural Network Constitutive Models in Principal Stretches
Computational Engineering, Finance, and Science
Teaches computers to predict how soft things bend.
Learning based convex approximation for constrained parametric optimization
Optimization and Control
Solves hard math problems with smart computer brains.
A Unified Approach to Enforce Non-Negativity Constraint in Neural Network Approximation for Optimal Voltage Regulation (preprint)
Systems and Control
Makes power grids more stable with renewable energy.