93 citations · 208 across the 9 of their papers we have counts for
9 papers
Local Learning Rules for Out-of-Equilibrium Physical Generative Models
Cyrill Bösch, Geoffrey Roeder, Marc Serra-Garcia +1
We show that the out-of-equilibrium driving protocol of score-based generative models (SGMs) can be learned via local learning rules. The gradient with respect to the parameters of…
Provably efficient variational generative modeling of quantum many-body systems via quantum-probabilistic information geometry
Faris M. Sbahi, Antonio J. Martinez, Sahil Patel +4
The dual tasks of quantum Hamiltonian learning and quantum Gibbs sampling are relevant to many important problems in physics and chemistry. In the low temperature regime, algorithm…
More Stiffness with Less Fiber: End-to-End Fiber Path Optimization for 3D-Printed Composites
Xingyuan Sun, Geoffrey Roeder, Tianju Xue +2
In 3D printing, stiff fibers (e.g., carbon fiber) can reinforce thermoplastic polymers with limited stiffness. However, existing commercial digital manufacturing software only prov…
Probabilistic Graphical Models and Tensor Networks: A Hybrid Framework
Jacob Miller, Geoffrey Roeder, Tai-Danae Bradley
We investigate a correspondence between two formalisms for discrete probabilistic modeling: probabilistic graphical models (PGMs) and tensor networks (TNs), a powerful modeling fra…
On Linear Identifiability of Learned Representations
Geoffrey Roeder, Luke Metz, Diederik P. Kingma
Identifiability is a desirable property of a statistical model: it implies that the true model parameters may be estimated to any desired precision, given sufficient computational…
Learning Composable Energy Surrogates for PDE Order Reduction
Alex Beatson, Jordan T. Ash, Geoffrey Roeder +2
Meta-materials are an important emerging class of engineered materials in which complex macroscopic behaviour--whether electromagnetic, thermal, or mechanical--arises from modular…
Efficient Amortised Bayesian Inference for Hierarchical and Nonlinear Dynamical Systems
Geoffrey Roeder, Paul K. Grant, Andrew Phillips +2
We introduce a flexible, scalable Bayesian inference framework for nonlinear dynamical systems characterised by distinct and hierarchical variability at the individual, group, and…
Backpropagation through the Void: Optimizing control variates for black-box gradient estimation
Will Grathwohl, Dami Choi, Yuhuai Wu +2
Gradient-based optimization is the foundation of deep learning and reinforcement learning. Even when the mechanism being optimized is unknown or not differentiable, optimization us…
Sticking the Landing: Simple, Lower-Variance Gradient Estimators for Variational Inference
Geoffrey Roeder, Yuhuai Wu, David Duvenaud
We propose a simple and general variant of the standard reparameterized gradient estimator for the variational evidence lower bound. Specifically, we remove a part of the total der…