Search Results for author: Patrick Forré

Found 21 papers, 12 papers with code

Self-Supervised Hybrid Inference in State-Space Models

no code implementations28 Jul 2021 David Ruhe, Patrick Forré

We can easily incorporate this knowledge into our model, leading to a hybrid inference approach.

Variational Inference

Truncated Marginal Neural Ratio Estimation

2 code implementations2 Jul 2021 Benjamin Kurt Miller, Alex Cole, Patrick Forré, Gilles Louppe, Christoph Weniger

Our approach is simulation efficient by simultaneously estimating low-dimensional marginal posteriors instead of the joint posterior and by proposing simulations targeted to an observation of interest via a prior suitably truncated by an indicator function.

Coordinate Independent Convolutional Networks -- Isometry and Gauge Equivariant Convolutions on Riemannian Manifolds

1 code implementation10 Jun 2021 Maurice Weiler, Patrick Forré, Erik Verlinde, Max Welling

We argue that the particular choice of coordinatization should not affect a network's inference -- it should be coordinate independent.

Transitional Conditional Independence

no code implementations23 Apr 2021 Patrick Forré

For this we introduce transition probability spaces and transitional random variables.

Efficient Causal Inference from Combined Observational and Interventional Data through Causal Reductions

no code implementations8 Mar 2021 Maximilian Ilse, Patrick Forré, Max Welling, Joris M. Mooij

We propose a learning algorithm to estimate the parameterized reduced model jointly from observational and interventional data.

Causal Inference

Argmax Flows and Multinomial Diffusion: Learning Categorical Distributions

2 code implementations10 Feb 2021 Emiel Hoogeboom, Didrik Nielsen, Priyank Jaini, Patrick Forré, Max Welling

Argmax Flows are defined by a composition of a continuous distribution (such as a normalizing flow), and an argmax function.

Denoising Language Modelling +1

Self Normalizing Flows

1 code implementation14 Nov 2020 T. Anderson Keller, Jorn W. T. Peters, Priyank Jaini, Emiel Hoogeboom, Patrick Forré, Max Welling

Efficient gradient computation of the Jacobian determinant term is a core problem in many machine learning settings, and especially so in the normalizing flow framework.

FlipOut: Uncovering Redundant Weights via Sign Flipping

no code implementations5 Sep 2020 Andrei Apostol, Maarten Stol, Patrick Forré

Modern neural networks, although achieving state-of-the-art results on many tasks, tend to have a large number of parameters, which increases training time and resource usage.

Object Classification

Neural Ordinary Differential Equations on Manifolds

no code implementations11 Jun 2020 Luca Falorsi, Patrick Forré

Normalizing flows are a powerful technique for obtaining reparameterizable samples from complex multimodal distributions.

Pruning via Iterative Ranking of Sensitivity Statistics

1 code implementation1 Jun 2020 Stijn Verdenius, Maarten Stol, Patrick Forré

With the introduction of SNIP [arXiv:1810. 02340v2], it has been demonstrated that modern neural networks can effectively be pruned before training.

Selecting Data Augmentation for Simulating Interventions

1 code implementation4 May 2020 Maximilian Ilse, Jakub M. Tomczak, Patrick Forré

We argue that causal concepts can be used to explain the success of data augmentation by describing how they can weaken the spurious correlation between the observed domains and the task labels.

Data Augmentation Domain Generalization

Reparameterizing Distributions on Lie Groups

1 code implementation7 Mar 2019 Luca Falorsi, Pim de Haan, Tim R. Davidson, Patrick Forré

Unfortunately, this research has primarily focused on distributions defined in Euclidean space, ruling out the usage of one of the most influential class of spaces with non-trivial topologies: Lie groups.

Pose Estimation

Causal Calculus in the Presence of Cycles, Latent Confounders and Selection Bias

no code implementations2 Jan 2019 Patrick Forré, Joris M. Mooij

We prove the main rules of causal calculus (also called do-calculus) for i/o structural causal models (ioSCMs), a generalization of a recently proposed general class of non-/linear structural causal models that allow for cycles, latent confounders and arbitrary probability distributions.

Selection bias

Sinkhorn AutoEncoders

2 code implementations ICLR 2019 Giorgio Patrini, Rianne van den Berg, Patrick Forré, Marcello Carioni, Samarth Bhargav, Max Welling, Tim Genewein, Frank Nielsen

We show that minimizing the p-Wasserstein distance between the generator and the true data distribution is equivalent to the unconstrained min-min optimization of the p-Wasserstein distance between the encoder aggregated posterior and the prior in latent space, plus a reconstruction error.

Probabilistic Programming

Explorations in Homeomorphic Variational Auto-Encoding

1 code implementation12 Jul 2018 Luca Falorsi, Pim de Haan, Tim R. Davidson, Nicola De Cao, Maurice Weiler, Patrick Forré, Taco S. Cohen

Our experiments show that choosing manifold-valued latent variables that match the topology of the latent data manifold, is crucial to preserve the topological structure and learn a well-behaved latent space.

Constraint-based Causal Discovery for Non-Linear Structural Causal Models with Cycles and Latent Confounders

1 code implementation9 Jul 2018 Patrick Forré, Joris M. Mooij

We address the problem of causal discovery from data, making use of the recently proposed causal modeling framework of modular structural causal models (mSCM) to handle cycles, latent confounders and non-linearities.

Causal Discovery

Markov Properties for Graphical Models with Cycles and Latent Variables

no code implementations24 Oct 2017 Patrick Forré, Joris M. Mooij

We investigate probabilistic graphical models that allow for both cycles and latent variables.

Foundations of Structural Causal Models with Cycles and Latent Variables

no code implementations18 Nov 2016 Stephan Bongers, Patrick Forré, Jonas Peters, Joris M. Mooij

In this paper, we investigate SCMs in a more general setting, allowing for the presence of both latent confounders and cycles.

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