
QuasiMeasurable Spaces
We introduce the categories of quasimeasurable spaces, which are slight...
read it

SelfSupervised Hybrid Inference in StateSpace Models
We perform approximate inference in statespace models that allow for no...
read it

Truncated Marginal Neural Ratio Estimation
Parametric stochastic simulators are ubiquitous in science, often featur...
read it

Coordinate Independent Convolutional Networks – Isometry and Gauge Equivariant Convolutions on Riemannian Manifolds
Motivated by the vast success of deep convolutional networks, there is a...
read it

An Informationtheoretic Approach to Distribution Shifts
Safely deploying machine learning models to the real world is often a ch...
read it

Transitional Conditional Independence
We develope the framework of transitional conditional independence. For ...
read it

Efficient Causal Inference from Combined Observational and Interventional Data through Causal Reductions
Unobserved confounding is one of the main challenges when estimating cau...
read it

Argmax Flows and Multinomial Diffusion: Towards NonAutoregressive Language Models
The field of language modelling has been largely dominated by autoregres...
read it

Self Normalizing Flows
Efficient gradient computation of the Jacobian determinant term is a cor...
read it

FlipOut: Uncovering Redundant Weights via Sign Flipping
Modern neural networks, although achieving stateoftheart results on m...
read it

Improving Fair Predictions Using Variational Inference In Causal Models
The importance of algorithmic fairness grows with the increasing impact ...
read it

Neural Ordinary Differential Equations on Manifolds
Normalizing flows are a powerful technique for obtaining reparameterizab...
read it

Pruning via Iterative Ranking of Sensitivity Statistics
With the introduction of SNIP [arXiv:1810.02340v2], it has been demonstr...
read it

Designing Data Augmentation for Simulating Interventions
Machine learning models trained with purely observational data and the p...
read it

Learning Robust Representations via MultiView Information Bottleneck
The information bottleneck principle provides an informationtheoretic m...
read it

Reparameterizing Distributions on Lie Groups
Reparameterizable densities are an important way to learn probability di...
read it

Causal Calculus in the Presence of Cycles, Latent Confounders and Selection Bias
We prove the main rules of causal calculus (also called docalculus) for...
read it

Sinkhorn AutoEncoders
Optimal Transport offers an alternative to maximum likelihood for learni...
read it

Explorations in Homeomorphic Variational AutoEncoding
The manifold hypothesis states that many kinds of highdimensional data ...
read it

Constraintbased Causal Discovery for NonLinear Structural Causal Models with Cycles and Latent Confounders
We address the problem of causal discovery from data, making use of the ...
read it

Markov Properties for Graphical Models with Cycles and Latent Variables
We investigate probabilistic graphical models that allow for both cycles...
read it
Patrick Forré
is this you? claim profile
Professor Faculty of Science Informatics Institute at University of Amsterdam