Metraipolis › archive › dc_4034cc669beb
Benchmarking Optimizers to Solve Inverse Problems with Differentiable Physics Simulators — arXiv:2609.13819
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.13819
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T00:10:29.380Z
- SHA-256 of the archived text
143279fb7144e43cd5188ccab11c68fdd94ed19db7cd612b72e7e88aeeb04e5a- Stable URL of this page
https://metraipolis.com/documento/dc_4034cc669beb
How to cite
Benchmarking Optimizers to Solve Inverse Problems with Differentiable Physics Simulators — arXiv:2609.13819 — arXiv (en), https://arxiv.org/abs/2609.13819 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4034cc669beb (Metraipolis archive dc_4034cc669beb, sha256 143279fb7144e43cd5188ccab11c68fdd94ed19db7cd612b72e7e88aeeb04e5a)
BibTeX
@misc{dc4034cc669beb,
title = {Benchmarking Optimizers to Solve Inverse Problems with Differentiable Physics Simulators — arXiv:2609.13819},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.13819},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4034cc669beb; sha256 143279fb7144e43cd5188ccab11c68fdd94ed19db7cd612b72e7e88aeeb04e5a},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.13819. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-15 in cs.LG). Categorie arXiv: Machine Learning (cs.LG) ; Optimization and Control (math.OC); Computational Physics (physics.comp-ph). Pagina del lavoro: https://arxiv.org/abs/2609.13819 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-15T23:54:14.641Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-15?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).