Add to ORKGBackground: Markov chain Monte Carlo (MCMC) methods for deep learning are not commonly used because of the computationally heavy Metropolis-Hastings (MH) test. MCMC methods can give more information in its predictions than variational inference. Different approximations of the MH-test have made algorithms that are tractable for deep learning but are still inefficient. Objective: This exploratory thesis will examine what makes different approximate MCMC methods efficient. Results: This work introduces a method called stochastic target Metropolis-Hastings (STMH). As it uses gradients to approximate the target in the MH algorithm, rather than approximating the MH-test, STMH is a faster method. When compared to stochastic gradient descent (SGD)...
Bayesian machine learning is a subfield of machine learning that incorporates Bayesian principles an...
In this work, we present, analyze, and implement a class of Multi-Level Markov chain Monte Carlo (ML...
The breakout success of deep neural networks (NNs) in the 2010's marked a new era in the quest to bu...
Deep learning models, such as convolutional neural networks, have long been applied to image and mul...
Modern deep learning methods constitute incredibly powerful tools to tackle a myriad of challenging ...
In this work, I will focus on ways in which we can build machine learning models that appropriately ...
We consider the problem of Bayesian parameter estimation for deep neural networks, which is importan...
Traditional algorithms for Bayesian posterior inference require processing the entire dataset in eac...
Traditional algorithms for Bayesian posterior inference require processing the entire dataset in eac...
Uncertainty estimation in deep models is essential in many real-world applications and has benefited...
Bayesian statistics has emerged as a leading paradigm for the analysis of complicated datasets and f...
285 pagesProbabilistic modeling, as known as probabilistic machine learning, provides a principled f...
Modern deep learning methods constitute incredibly powerful tools to tackle a myriad of challenging ...
In this article we consider Bayesian inference associated to deep neural networks (DNNs) and in part...
Deep Learning (DL) has achieved the state-of-the-art performance across a broad spectrum oftasks. Fr...
Bayesian machine learning is a subfield of machine learning that incorporates Bayesian principles an...
In this work, we present, analyze, and implement a class of Multi-Level Markov chain Monte Carlo (ML...
The breakout success of deep neural networks (NNs) in the 2010's marked a new era in the quest to bu...
Deep learning models, such as convolutional neural networks, have long been applied to image and mul...
Modern deep learning methods constitute incredibly powerful tools to tackle a myriad of challenging ...
In this work, I will focus on ways in which we can build machine learning models that appropriately ...
We consider the problem of Bayesian parameter estimation for deep neural networks, which is importan...
Traditional algorithms for Bayesian posterior inference require processing the entire dataset in eac...
Traditional algorithms for Bayesian posterior inference require processing the entire dataset in eac...
Uncertainty estimation in deep models is essential in many real-world applications and has benefited...
Bayesian statistics has emerged as a leading paradigm for the analysis of complicated datasets and f...
285 pagesProbabilistic modeling, as known as probabilistic machine learning, provides a principled f...
Modern deep learning methods constitute incredibly powerful tools to tackle a myriad of challenging ...
In this article we consider Bayesian inference associated to deep neural networks (DNNs) and in part...
Deep Learning (DL) has achieved the state-of-the-art performance across a broad spectrum oftasks. Fr...
Bayesian machine learning is a subfield of machine learning that incorporates Bayesian principles an...
In this work, we present, analyze, and implement a class of Multi-Level Markov chain Monte Carlo (ML...
The breakout success of deep neural networks (NNs) in the 2010's marked a new era in the quest to bu...