BDL

Bayesian neural networks and dimensionality reduction

In conducting non-linear dimensionality reduction and feature learning, it is common to suppose that the data lie near a …

Deborshee Sen, Theodore Papamarkou, David Dunson

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

Approximate blocked Gibbs sampling for Bayesian neural networks

In this work, minibatch MCMC sampling for feedforward neural networks is made more feasible. To this end, it is proposed to sample …

Theodore Papamarkou

The premise of approximate MCMC in Bayesian deep learning (UCSB)

Talk on an approximate MCMC sampling approach to Bayesian deep learning.

Sep 26, 2022 3:30 PM — 4:30 PM University of California, Santa Barbara, Department of Computer Science

The premise of approximate MCMC in Bayesian deep learning (University of Warwick)

Talk on an approximate MCMC sampling approach to Bayesian deep learning.

Sep 8, 2022 9:10 AM — 9:35 AM University of Warwick, Department of Statistics

Approximate MCMC for Bayesian deep learning

This project aims to develop approximate MCMC methods for Bayesian deep learning in order to quantify the uncertainty of predictions made by neural networks.

Approximate MCMC for Bayesian deep learning

Challenges in Markov chain Monte Carlo for Bayesian neural networks

Markov chain Monte Carlo (MCMC) methods have not been broadly adopted in Bayesian neural networks (BNNs). This paper initially reviews …

Theodore Papamarkou, Jacob Hinkle, M. Todd Young, David Womble

Challenges in Markov chain Monte Carlo for Bayesian neural networks

Talk on the predictive capacity of Bayesian marginalization for neural networks in the absence of MCMC convergence.

Apr 23, 2021 3:00 PM — 4:00 PM University of Glasgow, School of Mathematics and Statistics

Wide neural networks with bottlenecks are deep Gaussian processes

There has recently been much work on the ‘wide limit’ of neural networks, where Bayesian neural networks (BNNs) are shown …

Devanshu Agrawal, Theodore Papamarkou, Jacob Hinkle