no code implementations • 1 Feb 2024 • Theodore Papamarkou, Maria Skoularidou, Konstantina Palla, Laurence Aitchison, Julyan Arbel, David Dunson, Maurizio Filippone, Vincent Fortuin, Philipp Hennig, Jose Miguel Hernandez 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
In the current landscape of deep learning research, there is a predominant emphasis on achieving high predictive accuracy in supervised tasks involving large image and language datasets.
1 code implementation • NeurIPS 2023 • Michael Bereket, Theofanis Karaletsos
For example, in drug discovery, there is a need to model the effects of diverse interventions on cells in order to characterize unknown biological mechanisms of action.
no code implementations • 20 Oct 2023 • Benson Chen, Mohammad M. Sultan, Theofanis Karaletsos
DNA-Encoded Library (DEL) has proven to be a powerful tool that utilizes combinatorially constructed small molecules to facilitate highly-efficient screening assays.
1 code implementation • 28 Sep 2023 • Yujia Bao, Srinivasan Sivanandan, Theofanis Karaletsos
We evaluate the performance of ChannelViT on ImageNet, JUMP-CP (microscopy cell imaging), and So2Sat (satellite imaging).
1 code implementation • 30 May 2023 • Yujia Bao, Theofanis Karaletsos
Additionally, we introduce a context inference network to predict such tokens on-the-fly, given a batch of samples from the group.
1 code implementation • 30 Nov 2022 • Kirill Shmilovich, Benson Chen, Theofanis Karaletsos, Mohammad M. Sultan
Computational models have been deployed to learn the latent binding affinities that are correlated to the sequenced count data; however, this correlation is often obfuscated by various sources of noise introduced in its complicated data-generation process.
1 code implementation • 4 Nov 2022 • Dionysis Manousakas, Hippolyt Ritter, Theofanis Karaletsos
Recent advances in coreset methods have shown that a selection of representative datapoints can replace massive volumes of data for Bayesian inference, preserving the relevant statistical information and significantly accelerating subsequent downstream tasks.
1 code implementation • 1 Oct 2021 • Hippolyt Ritter, Theofanis Karaletsos
We introduce TyXe, a Bayesian neural network library built on top of Pytorch and Pyro.
no code implementations • 29 Sep 2021 • Samrudhdhi Bharatkumar Rangrej, Kevin J Liang, Xi Yin, Guan Pang, Theofanis Karaletsos, Lior Wolf, Tal Hassner
Few-shot learning (FSL) methods aim to generalize a model to new unseen classes using only a small number of support examples.
no code implementations • 17 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.
1 code implementation • 25 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.
1 code implementation • 9 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.
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.
no code implementations • 8 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.
no code implementations • pproximateinference AABI Symposium 2019 • Theofanis Karaletsos, Thang D. Bui
Bayesian inference offers a theoretically grounded and general way to train neural networks and can potentially give calibrated uncertainty.
no code implementations • 25 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.
no code implementations • 17 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.
no code implementations • 8 Dec 2018 • Christian F. Perez, Felipe Petroski Such, Theofanis Karaletsos
Traditional model-based RL relies on hand-specified or learned models of transition dynamics of the environment.
1 code implementation • 18 Oct 2018 • Eli Bingham, Jonathan P. Chen, Martin Jankowiak, Fritz Obermeyer, Neeraj Pradhan, Theofanis Karaletsos, Rohit Singh, Paul Szerlip, Paul Horsfall, Noah D. Goodman
Pyro is a probabilistic programming language built on Python as a platform for developing advanced probabilistic models in AI research.
no code implementations • 1 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.
no code implementations • 5 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.
2 code implementations • 23 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.
no code implementations • 15 Dec 2016 • Theofanis Karaletsos
A popular tool for learning implicit models are generative adversarial networks (GANs) which learn parameters of generators by fooling discriminators.
5 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.
no code implementations • 10 Feb 2016 • Stephanie L. Hyland, Theofanis Karaletsos, Gunnar Rätsch
Identifying relationships between concepts is a key aspect of scientific knowledge synthesis.
no code implementations • 1 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.
no code implementations • 16 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.
no code implementations • 28 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.