74 citations · 370 across the 44 of their papers we have counts for
23 papers · 1 filter
Amortized Structured Stochastic Variational Inference for Gaussian Process Latent Variable Models
Maksym Tretiakov, Sarah Filippi, Sarah Lucie Filipp +4
Many machine learning methods aim to approximate the lower-dimensional manifold on which the data lives. A desirable feature of such methods is that they should capture the epistem…
Estimating optimal PAC-Bayes bounds with Hamiltonian Monte Carlo
Szilvia Ujváry, Gergely Flamich, Vincent Fortuin +1
An important yet underexplored question in the PAC-Bayes literature is how much tightness we lose by restricting the posterior family to factorized Gaussian distributions when opti…
A Primer on Bayesian Neural Networks: Review and Debates
Julyan Arbel, Konstantinos Pitas, Mariia Vladimirova +1
Neural networks have achieved remarkable performance across various problem domains, but their widespread applicability is hindered by inherent limitations such as overconfidence i…
Understanding Pathologies of Deep Heteroskedastic Regression
Eliot Wong-Toi, Alex Boyd, Vincent Fortuin +1
Deep, overparameterized regression models are notorious for their tendency to overfit. This problem is exacerbated in heteroskedastic models, which predict both mean and residual n…
Improving Neural Additive Models with Bayesian Principles
Kouroche Bouchiat, Alexander Immer, Hugo Yèche +2
Neural additive models (NAMs) enhance the transparency of deep neural networks by handling input features in separate additive sub-networks. However, they lack inherent mechanisms…
Scalable PAC-Bayesian Meta-Learning via the PAC-Optimal Hyper-Posterior: From Theory to Practice
Jonas Rothfuss, Martin Josifoski, Vincent Fortuin +1
Meta-Learning aims to speed up the learning process on new tasks by acquiring useful inductive biases from datasets of related learning tasks. While, in practice, the number of rel…
Invariance Learning in Deep Neural Networks with Differentiable Laplace Approximations
Alexander Immer, Tycho F. A. van der Ouderaa, Gunnar Rätsch +2
Data augmentation is commonly applied to improve performance of deep learning by enforcing the knowledge that certain transformations on the input preserve the output. Currently, t…
Deep Classifiers with Label Noise Modeling and Distance Awareness
Vincent Fortuin, Mark Collier, Florian Wenzel +7
Uncertainty estimation in deep learning has recently emerged as a crucial area of interest to advance reliability and robustness in safety-critical applications. While there have b…
A Bayesian Approach to Invariant Deep Neural Networks
Nikolaos Mourdoukoutas, Marco Federici, Georges Pantalos +2
We propose a novel Bayesian neural network architecture that can learn invariances from data alone by inferring a posterior distribution over different weight-sharing schemes. We s…
Data augmentation in Bayesian neural networks and the cold posterior effect
Seth Nabarro, Stoil Ganev, Adrià Garriga-Alonso +3
Bayesian neural networks that incorporate data augmentation implicitly use a ``randomly perturbed log-likelihood [which] does not have a clean interpretation as a valid likelihood…
BNNpriors: A library for Bayesian neural network inference with different prior distributions
Vincent Fortuin, Adrià Garriga-Alonso, Mark van der Wilk +1
Bayesian neural networks have shown great promise in many applications where calibrated uncertainty estimates are crucial and can often also lead to a higher predictive performance…
Priors in Bayesian Deep Learning: A Review
Vincent Fortuin
While the choice of prior is one of the most critical parts of the Bayesian inference workflow, recent Bayesian deep learning models have often fallen back on vague priors, such as…
Scalable Marginal Likelihood Estimation for Model Selection in Deep Learning
Alexander Immer, Matthias Bauer, Vincent Fortuin +2
Marginal-likelihood based model-selection, even though promising, is rarely used in deep learning due to estimation difficulties. Instead, most approaches rely on validation data,…
On Disentanglement in Gaussian Process Variational Autoencoders
Simon Bing, Vincent Fortuin, Gunnar Rätsch
Complex multivariate time series arise in many fields, ranging from computer vision to robotics or medicine. Often we are interested in the independent underlying factors that give…
Exact Langevin Dynamics with Stochastic Gradients
Adrià Garriga-Alonso, Vincent Fortuin
Stochastic gradient Markov Chain Monte Carlo algorithms are popular samplers for approximate inference, but they are generally biased. We show that many recent versions of these me…
Bayesian Neural Network Priors Revisited
Vincent Fortuin, Adrià Garriga-Alonso, Sebastian W. Ober +5
Isotropic Gaussian priors are the de facto standard for modern Bayesian neural network inference. However, it is unclear whether these priors accurately reflect our true beliefs ab…
Factorized Gaussian Process Variational Autoencoders
Metod Jazbec, Michael Pearce, Vincent Fortuin
Variational autoencoders often assume isotropic Gaussian priors and mean-field posteriors, hence do not exploit structure in scenarios where we may expect similarity or consistency…
Sparse Gaussian Process Variational Autoencoders
Matthew Ashman, Jonathan So, Will Tebbutt +3
Large, multi-dimensional spatio-temporal datasets are omnipresent in modern science and engineering. An effective framework for handling such data are Gaussian process deep generat…
Scalable Gaussian Process Variational Autoencoders
Metod Jazbec, Matthew Ashman, Vincent Fortuin +3
Conventional variational autoencoders fail in modeling correlations between data points due to their use of factorized priors. Amortized Gaussian process inference through GP-VAEs…
PACOH: Bayes-Optimal Meta-Learning with PAC-Guarantees
Jonas Rothfuss, Vincent Fortuin, Martin Josifoski +1
Meta-learning can successfully acquire useful inductive biases from data. Yet, its generalization properties to unseen learning tasks are poorly understood. Particularly if the num…
GP-VAE: Deep Probabilistic Time Series Imputation
Vincent Fortuin, Dmitry Baranchuk, Gunnar Rätsch +1
Multivariate time series with missing values are common in areas such as healthcare and finance, and have grown in number and complexity over the years. This raises the question wh…
Meta-Learning Mean Functions for Gaussian Processes
Vincent Fortuin, Heiko Strathmann, Gunnar Rätsch
When fitting Bayesian machine learning models on scarce data, the main challenge is to obtain suitable prior knowledge and encode it into the model. Recent advances in meta-learnin…
Scalable Gaussian Processes on Discrete Domains
Vincent Fortuin, Gideon Dresdner, Heiko Strathmann +1
Kernel methods on discrete domains have shown great promise for many challenging data types, for instance, biological sequence data and molecular structure data. Scalable kernel me…