Accelerate Neural Subspace-Based Reduced-Order Solver of Deformable Simulation by Lipschitz Optimization

• URL: http://arxiv.org/abs/2409.03807v1
• Date: Thu, 5 Sep 2024 12:56:03 GMT
• Title: Accelerate Neural Subspace-Based Reduced-Order Solver of Deformable Simulation by Lipschitz Optimization
• Authors: Aoran Lyu, Shixian Zhao, Chuhua Xian, Zhihao Cen, Hongmin Cai, Guoxin Fang,
• Abstract summary: Reduced-order simulation is an emerging method for accelerating physical simulations with high DOFs. We propose a method for finding optimized subspace mappings, enabling further acceleration of neural reduced-order simulations. We demonstrate the effectiveness of our approach through general cases in both quasi-static and dynamics simulations.
• Score: 9.364019847856714
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Reduced-order simulation is an emerging method for accelerating physical simulations with high DOFs, and recently developed neural-network-based methods with nonlinear subspaces have been proven effective in diverse applications as more concise subspaces can be detected. However, the complexity and landscape of simulation objectives within the subspace have not been optimized, which leaves room for enhancement of the convergence speed. This work focuses on this point by proposing a general method for finding optimized subspace mappings, enabling further acceleration of neural reduced-order simulations while capturing comprehensive representations of the configuration manifolds. We achieve this by optimizing the Lipschitz energy of the elasticity term in the simulation objective, and incorporating the cubature approximation into the training process to manage the high memory and time demands associated with optimizing the newly introduced energy. Our method is versatile and applicable to both supervised and unsupervised settings for optimizing the parameterizations of the configuration manifolds. We demonstrate the effectiveness of our approach through general cases in both quasi-static and dynamics simulations. Our method achieves acceleration factors of up to 6.83 while consistently preserving comparable simulation accuracy in various cases, including large twisting, bending, and rotational deformations with collision handling. This novel approach offers significant potential for accelerating physical simulations, and can be a good add-on to existing neural-network-based solutions in modeling complex deformable objects.

Related papers

• Lattice real-time simulations with learned optimal kernels [49.1574468325115]
  We present a simulation strategy for the real-time dynamics of quantum fields inspired by reinforcement learning. It builds on the complex Langevin approach, which it amends with system specific prior information.
  arXiv  Detail & Related papers  (2023-10-12T06:01:01Z)
• Surrogate Neural Networks for Efficient Simulation-based Trajectory Planning Optimization [28.292234483886947]
  This paper presents a novel methodology that uses surrogate models in the form of neural networks to reduce the computation time of simulation-based optimization of a reference trajectory. We find a 74% better-performing reference trajectory compared to nominal, and the numerical results clearly show a substantial reduction in computation time for designing future trajectories.
  arXiv  Detail & Related papers  (2023-03-30T15:44:30Z)
• Guaranteed Conservation of Momentum for Learning Particle-based Fluid Dynamics [96.9177297872723]
  We present a novel method for guaranteeing linear momentum in learned physics simulations. We enforce conservation of momentum with a hard constraint, which we realize via antisymmetrical continuous convolutional layers. In combination, the proposed method allows us to increase the physical accuracy of the learned simulator substantially.
  arXiv  Detail & Related papers  (2022-10-12T09:12:59Z)
• Hybrid Physical-Neural ODEs for Fast N-body Simulations [0.22419496088582863]
  We present a new scheme to compensate for the small-scales approximations resulting from Particle-Mesh schemes for cosmological N-body simulations. We find that our approach outperforms PGD for the cross-correlation coefficients, and is more robust to changes in simulation settings.
  arXiv  Detail & Related papers  (2022-07-12T13:06:06Z)
• Efficient Differentiable Simulation of Articulated Bodies [89.64118042429287]
  We present a method for efficient differentiable simulation of articulated bodies. This enables integration of articulated body dynamics into deep learning frameworks. We show that reinforcement learning with articulated systems can be accelerated using gradients provided by our method.
  arXiv  Detail & Related papers  (2021-09-16T04:48:13Z)
• Hybridized Methods for Quantum Simulation in the Interaction Picture [69.02115180674885]
  We provide a framework that allows different simulation methods to be hybridized and thereby improve performance for interaction picture simulations. Physical applications of these hybridized methods yield a gate complexity scaling as $log2 Lambda$ in the electric cutoff. For the general problem of Hamiltonian simulation subject to dynamical constraints, these methods yield a query complexity independent of the penalty parameter $lambda$ used to impose an energy cost.
  arXiv  Detail & Related papers  (2021-09-07T20:01:22Z)
• Nonlinear model reduction for slow-fast stochastic systems near unknown invariant manifolds [4.565636963872865]
  We introduce a nonlinear model reduction technique for high-dimensional dynamical systems with a low-dimensional invariant effective manifold. We use a black box simulator from which short bursts of simulation can be obtained. A simulator is efficient in that it exploits the low dimension of the invariant manifold, and takes time steps of size dependent on the regularity of the effective process.
  arXiv  Detail & Related papers  (2021-04-05T19:29:46Z)
• Pushing the Envelope of Rotation Averaging for Visual SLAM [69.7375052440794]
  We propose a novel optimization backbone for visual SLAM systems. We leverage averaging to improve the accuracy, efficiency and robustness of conventional monocular SLAM systems. Our approach can exhibit up to 10x faster with comparable accuracy against the state-art on public benchmarks.
  arXiv  Detail & Related papers  (2020-11-02T18:02:26Z)
• Adaptive pruning-based optimization of parameterized quantum circuits [62.997667081978825]
  Variisy hybrid quantum-classical algorithms are powerful tools to maximize the use of Noisy Intermediate Scale Quantum devices. We propose a strategy for such ansatze used in variational quantum algorithms, which we call "Efficient Circuit Training" (PECT) Instead of optimizing all of the ansatz parameters at once, PECT launches a sequence of variational algorithms.
  arXiv  Detail & Related papers  (2020-10-01T18:14:11Z)
• Augmenting Differentiable Simulators with Neural Networks to Close the Sim2Real Gap [15.1962264049463]
  We present a differentiable simulation architecture for articulated rigid-body dynamics that enables the augmentation of analytical models with neural networks at any point of the computation.
  arXiv  Detail & Related papers  (2020-07-12T17:27:11Z)
• CoolMomentum: A Method for Stochastic Optimization by Langevin Dynamics with Simulated Annealing [23.87373187143897]
  Deep learning applications require global optimization of non- objective functions, which have multiple local minima. We show that a coordinate learning algorithm can be used to resolve the same problem in physical simulations.
  arXiv  Detail & Related papers  (2020-05-29T14:44:24Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.