Geoffrey Roeder
Cited by
Cited by
Backpropagation through the void: Optimizing control variates for black-box gradient estimation
W Grathwohl, D Choi, Y Wu, G Roeder, D Duvenaud
arXiv preprint arXiv:1711.00123, 2018
Sticking the landing: Simple, lower-variance gradient estimators for variational inference
G Roeder, Y Wu, DK Duvenaud
Advances in Neural Information Processing Systems, 6925-6934, 2017
Efficient amortised bayesian inference for hierarchical and nonlinear dynamical systems
G Roeder, PK Grant, A Phillips, N Dalchau, E Meeds
arXiv preprint arXiv:1905.12090, 2019
Learning Composable Energy Surrogates for PDE Order Reduction
A Beatson, JT Ash, G Roeder, T Xie, RP Adams
arXiv preprint arXiv:2005.06549, 2020
A data-driven computational scheme for the nonlinear mechanical properties of cellular mechanical metamaterials under large deformation
T Xue, A Beatson, M Chiaramonte, G Roeder, JT Ash, Y Menguc, ...
Soft matter 16 (32), 7524-7534, 2020
Modelling ordinary differential equations using a variational auto encoder
E Meeds, G Roeder, N Dalchau
US Patent App. 16/255,778, 2020
On linear identifiability of learned representations
G Roeder, L Metz, DP Kingma
arXiv preprint arXiv:2007.00810, 2020
Design Motifs for Probabilistic Generative Design
G Roeder, N Killoran, W Grathwohl, D Duvenaud
Climate models in modal adverbials: representational practice and deep uncertainty in the IPCC summary documents
GG Roeder
University of British Columbia, 2011
The system can't perform the operation now. Try again later.
Articles 1–9