Paper-Conference

Probability-generating function kernels for spherical data
The class of probability-generating function (PGF) kernels is introduced, which consists of kernels supported on the unit hypersphere, …
Theodore Papamarkou, Alexey Lindo
Cite Source Document
Connecting the dots: is mode-connectedness the key to feasible sample-based inference in Bayesian neural networks?
A major challenge in sample-based inference (SBI) for Bayesian neural networks is the size and structure of the networks’ parameter …
Emanuel Sommer, Lisa Wimmer, Theodore Papamarkou, Ludwig Bothmann, Bernd Bischl, David Rügamer
PDF Cite Source Document
Position: Bayesian deep learning is needed in the age of large-scale AI
In the current landscape of deep learning research, there is a predominant emphasis on achieving high predictive accuracy in supervised …
Theodore Papamarkou, Maria Skoularidou, Konstantina Palla, Laurence Aitchison, Julyan Arbel, David Dunson, Maurizio Filippone, Vincent Fortuin, Philipp Hennig, José Miguel Hernández-Lobato, Aliaksandr Hubin, Alexander Immer, Theofanis Karaletsos, Mohammad Emtiyaz Khan, Agustinus Kristiadi, Yingzhen Li, Stephan Mandt, Christopher Nemeth, Michael a Osborne, Tim G. J. Rudner, David Rügamer, Yee Whye Teh, Max Welling, Andrew Gordon Wilson, Ruqi Zhang
PDF Cite Source Document
Position: topological deep learning is the new frontier for relational learning
Topological deep learning (TDL) is a rapidly evolving field that uses topological features to understand and design deep learning …
Theodore Papamarkou, Tolga Birdal, Michael M. Bronstein, Gunnar E. Carlsson, Justin Curry, Yue Gao, Mustafa Hajij, Roland Kwitt, Pietro Lio, Paolo Di Lorenzo, Vasileios Maroulas, Nina Miolane, Farzana Nasrin, Karthikeyan Natesan Ramamurthy, Bastian Rieck, Simone Scardapane, Michael T Schaub, Petar Veličković, Bei Wang, Yusu Wang, Guowei Wei, Ghada Zamzmi
PDF Cite Source Document
Combinatorial complexes: bridging the gap between cell complexes and hypergraphs
Graph-based signal processing techniques have become essential for handling data in non-Euclidean spaces. However, there is a growing …
Mustafa Hajij, Ghada Zamzmi, Theodore Papamarkou, Aldo Guzman-Saenz, Tolga Birdal, Michael T. Schaub
Cite Source Document
Towards efficient MCMC sampling in Bayesian neural networks by exploiting symmetry
Bayesian inference in deep neural networks is challenging due to the high-dimensional, strongly multi-modal parameter posterior density …
Jonas Gregor Wiese, Lisa Wimmer, Theodore Papamarkou, Bernd Bischl, Stephan Günnemann, David Rügamer
Cite Source Document
Towards faster gene expression prediction via dimensionality reduction and feature selection
The majority of genes have a genetic component to their expression. Elastic nets have been shown effective at predicting …
Jeremy Watts, Elexis Allen, Ahmad Mitoubsi, Anahita Khojandi, James Eales, Theodore Papamarkou
Cite Source Document
Adapting random forests to predict obesity-associated gene expression
Random forests (RFs) are effective at predicting gene expression from genotype data. However, a comparison of RF regressors and …
Jeremy Watts, Elexis Allen, Ahmad Mitoubsi, Anahita Khojandi, James Eales, Farideh Jalali-Najafabadi, Theodore Papamarkou
Cite Source Document
Hidden Markov models as recurrent neural networks: an application to Alzheimer's disease
Hidden Markov models (HMMs) are commonly used for disease progression modeling when the true patient health state is not fully known. …
Matt Baucum, Anahita Khojandi, Theodore Papamarkou
Cite Source Document
Multiphase MCMC sampling for parameter inference in nonlinear ordinary differential equations
Traditionally, ODE parameter inference relies on solving the system of ODEs and assessing fit of the estimated signal with the …
Alan Lazarus, Dirk Husmeier, Theodore Papamarkou
PDF Cite Source Document