Benchmarking Optimizers to Solve Inverse Problems with Differentiable Physics Simulators

• URL: http://arxiv.org/abs/2609.13819v1
• Date: Sat, 12 Sep 2026 09:05:38 GMT
• Title: Benchmarking Optimizers to Solve Inverse Problems with Differentiable Physics Simulators
• Abstract summary: Solving problems with differentiable physics simulators holds the potential to revolutionize scientific discovery and engineering design.<n>We construct 12 differentiable physics simulators spanning physics domains including discrete mechanics, continuous mechanics, atomistic simulations, rendering, and semi-empirical physics models.<n>Based on these simulators, we design corresponding inverse problems that can be categorized into parameter identification, inverse design, and optimal control.
• Score: 7.108584753298545
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Solving inverse problems with differentiable physics simulators holds the potential to revolutionize scientific discovery and engineering design, as it enjoys both the strict physical correctness from rigorous numerical physics simulators, and the high efficiency and effectiveness from automatic differentiation and gradient-based optimization. However, currently, this paradigm faces performance issues in optimization. In this work, we target benchmarking the performance of different optimizers to solve various inverse problems. We construct 12 differentiable physics simulators spanning physics domains including discrete mechanics, continuous mechanics, atomistic simulations, rendering, and semi-empirical physics models. Based on these simulators, we design corresponding inverse problems that can be categorized into parameter identification, inverse design, and optimal control. Finally, we conduct extensive experiments to compare the performance of different optimizers, including regular first-order methods, approximate second-order methods, as well as global optimizers, on these inverse problems, and analyze the results to provide insights on how to choose and design optimizers for differentiable programming. We hope such benchmarks can inspire the development of more effective optimizers, and further promote the applications of differentiable programming in various scientific and engineering domains.

Related papers

• Robust Rigid Body Assembly via Contact-Implicit Optimal Control with Exact Second-Order Derivatives [0.9079873854272275]
  This paper proposes a sample-efficient robust optimal control approach for the determination of assembly motions.<n>A differentiable physics simulation is constructed that provides second-order analytic derivatives to the numerical solver.<n>The solution of the physics simulation problem is made differentiable by using smoothing inspired by interior-point methods applied to both the collision detection and the contact resolution problem.
  arXiv  Detail & Related papers  (2026-01-30T11:21:20Z)
• Optimizing Optimizers for Fast Gradient-Based Learning [53.81268610971847]
  We lay the theoretical foundation for automating design in gradient-based learning.<n>By treating gradient loss signals as a function that translates to parameter motions, the problem reduces to a family of convex optimization problems.
  arXiv  Detail & Related papers  (2025-12-06T09:50:41Z)
• Neural surrogates for designing gravitational wave detectors [21.601009915564344]
  We show how neural surrogate models can significantly reduce reliance on traditional, CPU-based simulators.<n>We train a neural network to surrogate the gravitational wave physics simulator Finesse, which was developed by the LIGO community.<n>Our algorithm loops between training the surrogate, inverse designing new experiments, and verifying their properties with the slow simulator for further training.
  arXiv  Detail & Related papers  (2025-11-24T17:58:59Z)
• DiffVL: Scaling Up Soft Body Manipulation using Vision-Language Driven Differentiable Physics [69.6158232150048]
  DiffVL is a method that enables non-expert users to communicate soft-body manipulation tasks. We leverage large language models to translate task descriptions into machine-interpretable optimization objectives.
  arXiv  Detail & Related papers  (2023-12-11T14:29:25Z)
• Efficient Inverse Design Optimization through Multi-fidelity Simulations, Machine Learning, and Search Space Reduction Strategies [0.8646443773218541]
  This paper introduces a methodology designed to augment the inverse design optimization process in scenarios constrained by limited compute. The proposed methodology is analyzed on two distinct engineering inverse design problems: airfoil inverse design and the scalar field reconstruction problem. Notably, this method is adaptable across any inverse design application, facilitating a synergy between a representative low-fidelity ML model, and high-fidelity simulation, and can be seamlessly applied across any variety of population-based optimization algorithms.
  arXiv  Detail & Related papers  (2023-12-06T18:20:46Z)
• Diffusion Generative Inverse Design [28.04683283070957]
  Inverse design refers to the problem of optimizing the input of an objective function in order to enact a target outcome. Recent developments in learned graph neural networks (GNNs) can be used for accurate, efficient, differentiable estimation of simulator dynamics. We show how denoising diffusion diffusion models can be used to solve inverse design problems efficiently and propose a particle sampling algorithm for further improving their efficiency.
  arXiv  Detail & Related papers  (2023-09-05T08:32:07Z)
• An Empirical Evaluation of Zeroth-Order Optimization Methods on AI-driven Molecule Optimization [78.36413169647408]
  We study the effectiveness of various ZO optimization methods for optimizing molecular objectives. We show the advantages of ZO sign-based gradient descent (ZO-signGD) We demonstrate the potential effectiveness of ZO optimization methods on widely used benchmark tasks from the Guacamol suite.
  arXiv  Detail & Related papers  (2022-10-27T01:58:10Z)
• 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)
• PlasticineLab: A Soft-Body Manipulation Benchmark with Differentiable Physics [89.81550748680245]
  We introduce a new differentiable physics benchmark called PasticineLab. In each task, the agent uses manipulators to deform the plasticine into the desired configuration. We evaluate several existing reinforcement learning (RL) methods and gradient-based methods on this benchmark.
  arXiv  Detail & Related papers  (2021-04-07T17:59:23Z)
• Scalable Differentiable Physics for Learning and Control [99.4302215142673]
  Differentiable physics is a powerful approach to learning and control problems that involve physical objects and environments. We develop a scalable framework for differentiable physics that can support a large number of objects and their interactions.
  arXiv  Detail & Related papers  (2020-07-04T19:07:51Z)

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.