Differentiate the Solver, Not the Equation: Reverse-Sweep Adjoints for Block Implicit Simulation

arXiv:2608.08559 · cs.GR, cs.LG, cs.NA, math.NA · Submitted 2026-08-09 · Read on arXiv

Lei Shu, Ying Jiang, Kui Wu, Yin Yang, Leonidas Guibas, Chenfanfu Jiang

cs.GR, cs.LG, cs.NA, math.NA

Submitted: 2026-08-09

Updated: 2026-08-11

Comments: 21 pages, 14 figures, 9 tables

Code: https://github.com/NVIDIA/warp

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

Adam — 18× in this paper · explained in 3 episodes
Inverse Problem — 7× in this paper · explained in 2 episodes
Composition — 6× in this paper · explained in 2 episodes
Harness — 3× in this paper · explained in 2 episodes
In International Conference on Machine Learning — 3× in this paper
Ablation — 2× in this paper · explained in 1 episode
Accuracy — 2× in this paper · explained in 1 episode
Allocator — 2× in this paper · explained in 2 episodes
Fixed Point — 2× in this paper · explained in 2 episodes
In International Conference on Learning Representations — 2× in this paper
Papers — 2× in this paper · explained in 3 episodes
System Identification — 2× in this paper · explained in 3 episodes
Trace — 2× in this paper · explained in 2 episodes
Benchmark — 1× in this paper · explained in 2 episodes
Generator — 1× in this paper · explained in 2 episodes
Parameterization — 1× in this paper · explained in 2 episodes
Regularization — 1× in this paper · explained in 3 episodes

Sources

Related papers