Hugging Face Trending Papers

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

Read the original on Hugging Face Trending Papers →

Differentiable simulation is a key component in learning, control, and inverse problems, where gradients through nonlinear implicit solvers are required. Existing approaches either rely on unrolled automatic differentiation, whose memory grows with solver depth, or on equation-level implicit differentiation, which assembles global Jacobians and solves large sparse adjoint systems, discarding the locality of the forward solver -- and differentiating the converged equation rather than the finite computation that actually ran.

Summary generated by The Flow from the publisher's feed. The full article lives at Hugging Face Trending Papers.

arXiv Machine Learning
Jun 29

Mosaic: A Benchmark Suite for Differentiable Physics Solvers

arXiv:2606. 27895v1 Announce Type: cross Abstract: Differentiable partial differential equation (PDE) solvers underpin solver-in-the-loop ML training, gradient-based optimal control, and inverse problems, yet the practical cost of obtaining correct, usable gradients from a given solver on a given problem is largely undocumented.

By Andrin Rehmann, Heiko Zimmermann, Dion H\"afner