6 citations · 9 across the 9 of their papers we have counts for
9 papers
Read, Write, Relax: Why Neural PDE Surrogates Need Both Global and Local Processing
Anuj Kumar, Heiko Zimmermann, Josiah Bjorgaard +4
Recent mesh-based simulation advances have, in no small part, relied on neural surrogates of two distinct families: global models that route information through a small set of late…
Mosaic: A Benchmark Suite for Differentiable Physics Solvers
Andrin Rehmann, Heiko Zimmermann, Dion Häfner
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…
Controlled Generation with Equivariant Variational Flow Matching
Floor Eijkelboom, Heiko Zimmermann, Sharvaree Vadgama +4
We derive a controlled generation objective within the framework of Variational Flow Matching (VFM), which casts flow matching as a variational inference problem. We demonstrate th…
VISA: Variational Inference with Sequential Sample-Average Approximations
Heiko Zimmermann, Christian A. Naesseth, Jan-Willem van de Meent
We present variational inference with sequential sample-average approximation (VISA), a method for approximate inference in computationally intensive models, such as those based on…
Topological Obstructions and How to Avoid Them
Babak Esmaeili, Robin Walters, Heiko Zimmermann +1
Incorporating geometric inductive biases into models can aid interpretability and generalization, but encoding to a specific geometric structure can be challenging due to the impos…
A Variational Perspective on Generative Flow Networks
Heiko Zimmermann, Fredrik Lindsten, Jan-Willem van de Meent +1
Generative flow networks (GFNs) are a class of models for sequential sampling of composite objects, which approximate a target distribution that is defined in terms of an energy fu…
Nested Variational Inference
Heiko Zimmermann, Hao Wu, Babak Esmaeili +1
We develop nested variational inference (NVI), a family of methods that learn proposals for nested importance samplers by minimizing an forward or reverse KL divergence at each lev…
Learning Proposals for Probabilistic Programs with Inference Combinators
Sam Stites, Heiko Zimmermann, Hao Wu +2
We develop operators for construction of proposals in probabilistic programs, which we refer to as inference combinators. Inference combinators define a grammar over importance sam…
Amortized Population Gibbs Samplers with Neural Sufficient Statistics
Hao Wu, Heiko Zimmermann, Eli Sennesh +2
We develop amortized population Gibbs (APG) samplers, a class of scalable methods that frames structured variational inference as adaptive importance sampling. APG samplers constru…