paper-with-me

Papers

PRDP: Progressively Refined Differentiable Physics

2025-02-26 · Kanishk Bhatia, Felix Koehler, Nils Thuerey

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%.

📄 PDF Abstract BibTeX arXiv:2502.19611

Code (1)

tum-pbs/prdp 공식 구현 jax

Tasks

Bilevel Optimization

Methods 이 논문이 사용한 방법론

Focus 설명 없음

Similar Papers 제목 키워드 기반

PRDP: Proximal Reward Difference Prediction for Large-Scale Reward Finetuning of Diffusion Models

2024-02-13 · CVPR 2024 1 · Fei Deng, Qifei Wang, Wei Wei, Matthias Grundmann 외

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

2023-03-27 · Sizhe Li, Zhiao Huang, Tao Chen, Tao Du 외

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 ManipulationObject

Physics-based Indirect Illumination for Inverse Rendering

2022-12-09 · Youming Deng, Xueting Li, Sifei Liu, Ming-Hsuan Yang

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 Synthesis

Physics-Informed Tracking (PIT)

2026-04-18 · Emil Hovad, Allan Peter Engsig-Karup arxiv

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 Reconstruction

Predicting Physical Object Properties from Video

2022-06-02 · Martin Link, Max Schwarz, Sven Behnke

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