1 code implementation • 22 Feb 2024 • Maksim Zhdanov, David Ruhe, Maurice Weiler, Ana Lucic, Johannes Brandstetter, Patrick Forré
We present Clifford-Steerable Convolutional Neural Networks (CS-CNNs), a novel class of $\mathrm{E}(p, q)$-equivariant CNNs.
1 code implementation • 15 Feb 2024 • Cong Liu, David Ruhe, Floor Eijkelboom, Patrick Forré
Experimental results show that our method is able to outperform both equivariant and simplicial graph neural networks on a variety of geometric tasks.
no code implementations • 21 Nov 2023 • Miriam Rateike, Isabel Valera, Patrick Forré
Neglecting the effect that decisions have on individuals (and thus, on the underlying data distribution) when designing algorithmic decision-making policies may increase inequalities and unfairness in the long term - even if fairness considerations were taken in the policy design process.
1 code implementation • 10 Nov 2023 • Metod Jazbec, Patrick Forré, Stephan Mandt, Dan Zhang, Eric Nalisnick
Early-exit neural networks (EENNs) facilitate adaptive inference by producing predictions at multiple stages of the forward pass.
no code implementations • 30 Oct 2023 • Teodora Pandeva, Patrick Forré, Aaditya Ramdas, Shubhanshu Shekhar
We propose a general framework for constructing powerful, sequential hypothesis tests for a large class of nonparametric testing problems.
no code implementations • 17 Oct 2023 • Mircea Mironenco, Patrick Forré
Using the structure and geometry of Lie groups and their homogeneous spaces, we present a framework by which it is possible to work with such groups primarily focusing on the Lie groups $G = \text{GL}^{+}(n, \mathbb{R})$ and $G = \text{SL}(n, \mathbb{R})$, as well as their representation as affine transformations $\mathbb{R}^{n} \rtimes G$.
no code implementations • 3 Oct 2023 • Benjamin Kurt Miller, Marco Federici, Christoph Weniger, Patrick Forré
The objective recovers Neural Posterior Estimation when the model class is normalized and unifies it with Neural Ratio Estimation, combining both into a single objective.
no code implementations • 13 Sep 2023 • Marco Federici, Patrick Forré, Ryota Tomioka, Bastiaan S. Veeling
Markov processes are widely used mathematical models for describing dynamic systems in various fields.
no code implementations • 1 Jun 2023 • Marco Federici, David Ruhe, Patrick Forré
Estimating the mutual information from samples from a joint distribution is a challenging problem in both science and engineering.
1 code implementation • 21 Apr 2023 • Arnaud Delaunoy, Benjamin Kurt Miller, Patrick Forré, Christoph Weniger, Gilles Louppe
We show empirically that the balanced versions tend to produce conservative posterior approximations on a wide variety of benchmarks.
1 code implementation • 15 Nov 2022 • David Ruhe, Kaze Wong, Miles Cranmer, Patrick Forré
We propose parameterizing the population distribution of the gravitational wave population modeling framework (Hierarchical Bayesian Analysis) with a normalizing flow.
no code implementations • 8 Nov 2022 • Fiona Lippert, Bart Kranstauber, E. Emiel van Loon, Patrick Forré
Under the assumption that the latent system dynamics are well approximated by a locally linear Gaussian transition model, we perform efficient posterior estimation using the classical Kalman smoother.
no code implementations • 24 Oct 2022 • Teodora Pandeva, Tim Bakker, Christian A. Naesseth, Patrick Forré
We introduce a powerful deep classifier two-sample test for high-dimensional data based on E-values, called E-value Classifier Two-Sample Test (E-C2ST).
1 code implementation • 11 Oct 2022 • Benjamin Kurt Miller, Christoph Weniger, Patrick Forré
Likelihood-to-evidence ratio estimation is usually cast as either a binary (NRE-A) or a multiclass (NRE-B) classification task.
no code implementations • 11 Oct 2022 • Kaitlin Maile, Dennis G. Wilson, Patrick Forré
Incorporating equivariance to symmetry groups as a constraint during neural network training can improve performance and generalization for tasks exhibiting those symmetries, but such symmetries are often not perfectly nor explicitly present.
1 code implementation • 5 Oct 2022 • Jim Boelrijk, Bernd Ensing, Patrick Forré
We also apply and compare our methods to state-of-the-art multi-objective BO methods and EAs on a range of synthetic benchmark test cases.
no code implementations • 5 Oct 2022 • Teodora Pandeva, Patrick Forré
Independent component analysis (ICA) is a blind source separation method for linear disentanglement of independent latent sources from observed data.
no code implementations • 29 Sep 2021 • Eva Smit, Thomas Gärtner, Patrick Forré
With the help of the implicit function theorem we show how, using a diverse set of models that have already been trained on the data, to select a pair of data points that have a common value of interpretable factors.
no code implementations • ICLR 2022 • David Ruhe, Patrick Forré
Additionally, using an approximate conditional independence, we can perform smoothing without having to parameterize a separate model.
2 code implementations • NeurIPS 2021 • Benjamin Kurt Miller, Alex Cole, Patrick Forré, Gilles Louppe, Christoph Weniger
Parametric stochastic simulators are ubiquitous in science, often featuring high-dimensional input parameters and/or an intractable likelihood.
1 code implementation • 10 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.
1 code implementation • NeurIPS 2021 • Marco Federici, Ryota Tomioka, Patrick Forré
Safely deploying machine learning models to the real world is often a challenging process.
no code implementations • 23 Apr 2021 • Patrick Forré
For this we introduce transition probability spaces and transitional random variables.
1 code implementation • ICLR Workshop GTRL 2021 • Jose Gallego-Posada, Patrick Forré
Inspired by the fuzzy topological representation of a dataset employed in UMAP (McInnes et al., 2018), we propose a regularization principle for supervised learning based on the preservation of the simplicial complex structure of the data.
1 code implementation • 8 Mar 2021 • Maximilian Ilse, Patrick Forré, Max Welling, Joris M. Mooij
Second, for continuous variables and assuming a linear-Gaussian model, we derive equality constraints for the parameters of the observational and interventional distributions.
2 code implementations • NeurIPS 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.
no code implementations • pproximateinference AABI Symposium 2021 • Emiel Hoogeboom, Didrik Nielsen, Priyank Jaini, Patrick Forré, Max Welling
This paper introduces a new method to define and train continuous distributions such as normalizing flows directly on categorical data, for example text and image segmentation.
1 code implementation • 14 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.
no code implementations • 5 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.
1 code implementation • 25 Aug 2020 • Rik Helwegen, Christos Louizos, Patrick Forré
Recent work on fairness metrics shows the need for causal reasoning in fairness constraints.
no code implementations • 11 Jun 2020 • Luca Falorsi, Patrick Forré
Normalizing flows are a powerful technique for obtaining reparameterizable samples from complex multimodal distributions.
1 code implementation • 1 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.
1 code implementation • 4 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.
3 code implementations • ICLR 2020 • Marco Federici, Anjan Dutta, Patrick Forré, Nate Kushman, Zeynep Akata
This enables us to identify superfluous information as that not shared by both views.
1 code implementation • 7 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.
no code implementations • 2 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.
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.
1 code implementation • 12 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.
1 code implementation • 9 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.
no code implementations • 24 Oct 2017 • Patrick Forré, Joris M. Mooij
We investigate probabilistic graphical models that allow for both cycles and latent variables.
no code implementations • 18 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.