Search Results for author: Theofanis Karaletsos

Found 21 papers, 6 papers with code

TyXe: Pyro-based Bayesian neural nets for Pytorch

1 code implementation1 Oct 2021 Hippolyt Ritter, Theofanis Karaletsos

We introduce TyXe, a Bayesian neural network library built on top of Pytorch and Pyro.

Continual Learning Image Classification

Localized Uncertainty Attacks

no code implementations17 Jun 2021 Ousmane Amadou Dia, Theofanis Karaletsos, Caner Hazirbas, Cristian Canton Ferrer, Ilknur Kaynar Kabul, Erik Meijer

Under this threat model, we create adversarial examples by perturbing only regions in the inputs where a classifier is uncertain.

Stochastic Aggregation in Graph Neural Networks

1 code implementation25 Feb 2021 Yuanqing Wang, Theofanis Karaletsos

Graph neural networks (GNNs) manifest pathologies including over-smoothing and limited discriminating power as a result of suboptimally expressive aggregating mechanisms.

Variational Inference

Variational Auto-Regressive Gaussian Processes for Continual Learning

1 code implementation9 Jun 2020 Sanyam Kapoor, Theofanis Karaletsos, Thang D. Bui

Through sequential construction of posteriors on observing data online, Bayes' theorem provides a natural framework for continual learning.

Bayesian Inference Continual Learning +1

Hierarchical Gaussian Process Priors for Bayesian Neural Network Weights

no code implementations NeurIPS 2020 Theofanis Karaletsos, Thang D. Bui

Probabilistic neural networks are typically modeled with independent weight priors, which do not capture weight correlations in the prior and do not provide a parsimonious interface to express properties in function space.

Active Learning

Generalized Hidden Parameter MDPs Transferable Model-based RL in a Handful of Trials

no code implementations8 Feb 2020 Christian F. Perez, Felipe Petroski Such, Theofanis Karaletsos

There is broad interest in creating RL agents that can solve many (related) tasks and adapt to new tasks and environments after initial training.

Gaussian Process Meta-Representations Of Neural Networks

no code implementations25 Sep 2019 Theofanis Karaletsos, Thang Bui

Bayesian inference offers a theoretically grounded and general way to train neural networks and can potentially give calibrated uncertainty.

Active Learning Bayesian Inference +1

Applying SVGD to Bayesian Neural Networks for Cyclical Time-Series Prediction and Inference

no code implementations17 Jan 2019 Xinyu Hu, Paul Szerlip, Theofanis Karaletsos, Rohit Singh

A regression-based BNN model is proposed to predict spatiotemporal quantities like hourly rider demand with calibrated uncertainties.

Time Series Time Series Prediction

Probabilistic Meta-Representations Of Neural Networks

no code implementations1 Oct 2018 Theofanis Karaletsos, Peter Dayan, Zoubin Ghahramani

Existing Bayesian treatments of neural networks are typically characterized by weak prior and approximate posterior distributions according to which all the weights are drawn independently.

Pathwise Derivatives for Multivariate Distributions

no code implementations5 Jun 2018 Martin Jankowiak, Theofanis Karaletsos

We exploit the link between the transport equation and derivatives of expectations to construct efficient pathwise gradient estimators for multivariate distributions.

Variational Inference

Likelihood-free inference with emulator networks

2 code implementations23 May 2018 Jan-Matthis Lueckmann, Giacomo Bassetto, Theofanis Karaletsos, Jakob H. Macke

Approximate Bayesian Computation (ABC) provides methods for Bayesian inference in simulation-based stochastic models which do not permit tractable likelihoods.

Bayesian Inference

Adversarial Message Passing For Graphical Models

no code implementations15 Dec 2016 Theofanis Karaletsos

A popular tool for learning implicit models are generative adversarial networks (GANs) which learn parameters of generators by fooling discriminators.

Probabilistic Programming

Conditional Similarity Networks

4 code implementations CVPR 2017 Andreas Veit, Serge Belongie, Theofanis Karaletsos

A main reason for this is that contradicting notions of similarities cannot be captured in a single space.

A Generative Model of Words and Relationships from Multiple Sources

no code implementations1 Oct 2015 Stephanie L. Hyland, Theofanis Karaletsos, Gunnar Rätsch

We propose a generative model which integrates evidence from diverse data sources, enabling the sharing of semantic information.

Link Prediction

Bayesian representation learning with oracle constraints

no code implementations16 Jun 2015 Theofanis Karaletsos, Serge Belongie, Gunnar Rätsch

Representation learning systems typically rely on massive amounts of labeled data in order to be trained to high accuracy.

Metric Learning Representation Learning

Automatic Relevance Determination For Deep Generative Models

no code implementations28 May 2015 Theofanis Karaletsos, Gunnar Rätsch

A recurring problem when building probabilistic latent variable models is regularization and model selection, for instance, the choice of the dimensionality of the latent space.

Model Selection Variational Inference

Cannot find the paper you are looking for? You can Submit a new open access paper.