PRDP: Progressively Refined Differentiable Physics
The physics solvers employed for neural network training are primarily iterative, and hence, differentiating through them introduces a severe computational burden as iterations grow large. Inspired by works in bilevel optimization, we show that full accuracy of the network is achievable through physics significantly coarser than fully converged solvers. We propose Progressively Refined Differentiable Physics (PRDP), an approach that identifies the level of physics refinement sufficient for full training accuracy. By beginning with coarse physics, adaptively refining it during training, and stopping refinement at the level adequate for training, it enables significant compute savings without sacrificing network accuracy. Our focus is on differentiating iterative linear solvers for sparsely discretized differential operators, which are fundamental to scientific computing. PRDP is applicable to both unrolled and implicit differentiation. We validate its performance on a variety of learning scenarios involving differentiable physics solvers such as inverse problems, autoregressive neural emulators, and correction-based neural-hybrid solvers. In the challenging example of emulating the Navier-Stokes equations, we reduce training time by 62%.
Code (1)
Tasks
Bilevel OptimizationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
PRDP: Proximal Reward Difference Prediction for Large-Scale Reward Finetuning of Diffusion Models
Reward finetuning has emerged as a promising approach to aligning foundation models with downstream objectives. Remarkable success has been achieved in the language domain by using reinforcement learning (RL) to maximize…
DenoisingReinforcement Learning (RL)DexDeform: Dexterous Deformable Object Manipulation with Human Demonstrations and Differentiable Physics
In this work, we aim to learn dexterous manipulation of deformable objects using multi-fingered hands. Reinforcement learning approaches for dexterous rigid object manipulation would struggle in this setting due to the c…
Deformable Object ManipulationObjectPhysics-based Indirect Illumination for Inverse Rendering
We present a physics-based inverse rendering method that learns the illumination, geometry, and materials of a scene from posed multi-view RGB images. To model the illumination of a scene, existing inverse rendering work…
Efficient Neural NetworkInverse RenderingNovel View SynthesisPhysics-Informed Tracking (PIT)
We propose Physics-Informed Tracking (PIT), a video-based framework for tracking a single particle from video, where a neural network autoencoder localizes a particle as a heatmap peak (landmark) and a differentiable phy…
Image ReconstructionPredicting Physical Object Properties from Video
We present a novel approach to estimating physical properties of objects from video. Our approach consists of a physics engine and a correction estimator. Starting from the initial observed state, object behavior is simu…
Hyperparameter OptimizationObject