Geoffrey Roeder

Physics and Astronomy · Physical Sciences

7h-index302citations17works1.02yr avg
OpenAlex↗ORCID↗Google Scholar↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Model Reduction and Neural Networks(4), Neural Networks and Applications(3), Machine Learning in Materials Science(3), Gaussian Processes and Bayesian Inference(3), Statistical Methods and Inference(2)

Publications17 total

Local Learning Rules for Out-of-Equilibrium Physical Generative Models
arXiv (Cornell University)·2025· 1 citedOpen Access
More Stiffness with Less Fiber: End-to-End Fiber Path Optimization for 3D-Printed Composites
2023· 9 citedOpen Access
Provably efficient variational generative modeling of quantum many-body systems via quantum-probabilistic information geometry
arXiv (Cornell University)·2022· 2 citedOpen Access
Probabilistic Graphical Models and Tensor Networks: A Hybrid Framework
arXiv (Cornell University)·2021· 4 citedOpen Access
On Linear Identifiability of Learned Representations
International Conference on Machine Learning·2021· 3 cited
Quantum Machine Learning with Quantum-Probabilistic Generative Models
Bulletin of the American Physical Society·2021
Learning Composable Energy Surrogates for PDE Order Reduction
Rare & Special e-Zone (The Hong Kong University of Science and Technology)·2020· 6 cited
On Linear Identifiability of Learned Representations
arXiv (Cornell University)·2020· 16 citedOpen Access
Learning Composable Energy Surrogates for PDE Order Reduction
arXiv (Cornell University)·2020· 4 citedOpen Access
A data-driven computational scheme for the nonlinear mechanical properties of cellular mechanical metamaterials under large deformation
Soft Matter·2020· 47 citedOpen Access
Efficient Amortised Bayesian Inference for Hierarchical and Nonlinear Dynamical Systems
arXiv (Cornell University)·2019· 10 citedOpen Access
Efficient Amortised Bayesian Inference for Hierarchical and Nonlinear\n Dynamical Systems
arXiv (Cornell University)·2019· 4 citedOpen Access
Backpropagation through the Void: Optimizing control variates for black-box gradient estimation
arXiv (Cornell University)·2017· 99 citedOpen Access
Sticking the Landing: Simple, Lower-Variance Gradient Estimators for Variational Inference
arXiv (Cornell University)·2017· 73 citedOpen Access
Sticking the Landing: An Asymptotically Zero-Variance Gradient Estimator for Variational Inference.
arXiv (Cornell University)·2017· 7 citedOpen Access
Sticking the Landing: Simple, Lower-Variance Gradient Estimators for\n Variational Inference
arXiv (Cornell University)·2017· 17 citedOpen Access
REDUCTION OF ENERGY REQUIREMENTS WITH REGENERATIVE BRAKING ON ELECTRIC VEHICLES
Elektrische Bahnen·1979

Frequent Co-authors

Ryan P. Adams(5), Yuhuai Wu(4), David Duvenaud(4), Tianju Xue(4), Alex Beatson(3), Jordan T. Ash(3), Luke Metz(2), Diederik P. Kingma(2), Paul K. Grant(2), Neil Dalchau(2), Edward Meeds(2), Will Grathwohl(1), Dami Choi(1), Maurizio M. Chiaramonte(1), Yiğit Mengüç(1), Sigrid Adriaenssens(1), Sheng Mao(1), Andrew Phillips(1), Xingyuan Sun(1), Szymon Rusinkiewicz(1)