no code implementations • 29 Sep 2021 • Joey Bose, Ricardo Pio Monti, Aditya Grover
Deep generative models excel at generating complex, high-dimensional data, often exhibiting impressive generalization beyond the training distribution.
2 code implementations • 4 Nov 2020 • Ilyes Khemakhem, Ricardo Pio Monti, Robert Leech, Aapo Hyvärinen
We exploit the fact that autoregressive flow architectures define an ordering over variables, analogous to a causal ordering, to show that they are well-suited to performing a range of causal inference tasks, ranging from causal discovery to making interventional and counterfactual predictions.
1 code implementation • 20 Jul 2020 • Pedro F. da Costa, Romy Lorenz, Ricardo Pio Monti, Emily Jones, Robert Leech
Formally, we employ Bayesian optimization to efficiently search the latent space of state-of-the-art GAN models, with the aim to automatically generate novel faces, to maximize an individual subject's response.
2 code implementations • 18 Jul 2020 • Ricardo Pio Monti, Ilyes Khemakhem, Aapo Hyvarinen
We posit that autoregressive flow models are well-suited to performing a range of causal inference tasks - ranging from causal discovery to making interventional and counterfactual predictions.
1 code implementation • NeurIPS 2020 • Ilyes Khemakhem, Ricardo Pio Monti, Diederik P. Kingma, Aapo Hyvärinen
We consider the identifiability theory of probabilistic models and establish sufficient conditions under which the representations learned by a very broad family of conditional energy-based models are unique in function space, up to a simple transformation.
2 code implementations • 10 Jul 2019 • Ilyes Khemakhem, Diederik P. Kingma, Ricardo Pio Monti, Aapo Hyvärinen
We address this issue by showing that for a broad family of deep latent-variable models, identification of the true joint distribution over observed and latent variables is actually possible up to very simple transformations, thus achieving a principled and powerful form of disentanglement.
no code implementations • 19 Apr 2019 • Ricardo Pio Monti, Kun Zhang, Aapo Hyvarinen
We consider the problem of inferring causal relationships between two or more passively observed variables.
no code implementations • 24 May 2018 • Ricardo Pio Monti, Aapo Hyvärinen
We propose a probabilistic model which simultaneously performs both a grouping of variables (i. e., detecting community structure) and estimation of connectivities between the groups which correspond to latent variables.
no code implementations • ICLR 2018 • Ricardo Pio Monti, Sina Tootoonian, Robin Cao
A widely observed phenomenon in deep learning is the degradation problem: increasing the depth of a network leads to a decrease in performance on both test and training data.
no code implementations • 28 Oct 2016 • Ricardo Pio Monti, Christoforos Anagnostopoulos, Giovanni Montana
In this work consider the problem of learning $\ell_1$ regularized linear models in the context of streaming data.
no code implementations • 1 May 2016 • Ricardo Pio Monti, Romy Lorenz, Robert Leech, Christoforos Anagnostopoulos, Giovanni Montana
Large-scale automated meta-analysis of neuroimaging data has recently established itself as an important tool in advancing our understanding of human brain function.
no code implementations • 7 Dec 2015 • Ricardo Pio Monti, Christoforos Anagnostopoulos, Giovanni Montana
In neuroimaging data analysis, Gaussian graphical models are often used to model statistical dependencies across spatially remote brain regions known as functional connectivity.
no code implementations • 6 Nov 2015 • Ricardo Pio Monti, Romy Lorenz, Robert Leech, Christoforos Anagnostopoulos, Giovanni Montana
We propose a framework to perform streaming covariance selection.
no code implementations • 8 Feb 2015 • Ricardo Pio Monti, Romy Lorenz, Christoforos Anagnostopoulos, Robert Leech, Giovanni Montana
Such studies have recently gained momentum and have been applied in a wide variety of settings; ranging from training of healthy subjects to self-regulate neuronal activity to being suggested as potential treatments for clinical populations.
no code implementations • 14 Oct 2013 • Ricardo Pio Monti, Peter Hellyer, David Sharp, Robert Leech, Christoforos Anagnostopoulos, Giovanni Montana
We apply the SINGLE algorithm to functional MRI data from 24 healthy patients performing a choice-response task to demonstrate the dynamic changes in network structure that accompany a simple but attentionally demanding cognitive task.