Patrick Forré
YOU?
Author Swipe
View article: Möbius transforms and Shapley values for vector-valued functions on weighted directed acyclic multigraphs
Möbius transforms and Shapley values for vector-valued functions on weighted directed acyclic multigraphs Open
We generalize the concept of Möbius inversion and Shapley values to directed acyclic multigraphs and weighted versions thereof. We further allow value functions (games) and thus their Möbius transforms (synergy function) and Shapley values…
View article: AdS-GNN -- a Conformally Equivariant Graph Neural Network
AdS-GNN -- a Conformally Equivariant Graph Neural Network Open
Conformal symmetries, i.e.\ coordinate transformations that preserve angles, play a key role in many fields, including physics, mathematics, computer vision and (geometric) machine learning. Here we build a neural network that is equivaria…
View article: Information Decomposition Diagrams Applied beyond Shannon Entropy: A Generalization of Hu's Theorem
Information Decomposition Diagrams Applied beyond Shannon Entropy: A Generalization of Hu's Theorem Open
In information theory, one major goal is to find useful functions that summarize the amount of information contained in the interaction of several random variables. Specifically, one can ask how the classical Shannon entropy, mutual inform…
View article: Comparison of optimization algorithms for automated method development of gradient profiles
Comparison of optimization algorithms for automated method development of gradient profiles Open
Optimization algorithms play an important role in method development workflows for gradient elution liquid chromatography. Their effectiveness has not been evaluated for chromatographic method development using standardized comparisons acr…
View article: Are Bayesian networks typically faithful?
Are Bayesian networks typically faithful? Open
Faithfulness is a ubiquitous assumption in causal inference, often motivated by the fact that the faithful parameters of linear Gaussian and discrete Bayesian networks are typical, and the folklore belief that this should also hold for oth…
View article: Robust Multi-view Co-expression Network Inference
Robust Multi-view Co-expression Network Inference Open
Unraveling the co-expression of genes across studies enhances the understanding of cellular processes. Inferring gene co-expression networks from transcriptome data presents many challenges, including spurious gene correlations, sample cor…
View article: Towards detailed and interpretable hybrid modeling of continental-scale bird migration
Towards detailed and interpretable hybrid modeling of continental-scale bird migration Open
Hybrid modeling aims to augment traditional theory-driven models with machine learning components that learn unknown parameters, sub-models or correction terms from data. In this work, we build on FluxRGNN, a recently developed hybrid mode…
View article: Abstract Markov Random Fields
Abstract Markov Random Fields Open
Markov random fields are known to be fully characterized by properties of their information diagrams, or I-diagrams. In particular, for Markov random fields, regions in the I-diagram corresponding to disconnected vertex sets in the graph v…
View article: The Perils of Optimizing Learned Reward Functions: Low Training Error Does Not Guarantee Low Regret
The Perils of Optimizing Learned Reward Functions: Low Training Error Does Not Guarantee Low Regret Open
In reinforcement learning, specifying reward functions that capture the intended task can be very challenging. Reward learning aims to address this issue by learning the reward function. However, a learned reward model may have a low error…
View article: Multivector Neurons: Better and Faster O(n)-Equivariant Clifford Graph Neural Networks
Multivector Neurons: Better and Faster O(n)-Equivariant Clifford Graph Neural Networks Open
Most current deep learning models equivariant to $O(n)$ or $SO(n)$ either consider mostly scalar information such as distances and angles or have a very high computational complexity. In this work, we test a few novel message passing graph…
View article: Designing Long-term Group Fair Policies in Dynamical Systems
Designing Long-term Group Fair Policies in Dynamical Systems Open
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 conside…
View article: Clifford-Steerable Convolutional Neural Networks
Clifford-Steerable Convolutional Neural Networks Open
We present Clifford-Steerable Convolutional Neural Networks (CS-CNNs), a novel class of $\mathrm{E}(p, q)$-equivariant CNNs. CS-CNNs process multivector fields on pseudo-Euclidean spaces $\mathbb{R}^{p,q}$. They cover, for instance, $\math…
View article: Enhancing LC×LC separations through Multi-Task Bayesian Optimization
Enhancing LC×LC separations through Multi-Task Bayesian Optimization Open
Method development in comprehensive two-dimensional liquid chromatography (LC×LC) is a challenging process. The interdependencies between the two dimensions and the possibility of incorporating complex gradient profiles, such as multi-segm…
View article: Clifford Group Equivariant Simplicial Message Passing Networks
Clifford Group Equivariant Simplicial Message Passing Networks Open
We introduce Clifford Group Equivariant Simplicial Message Passing Networks, a method for steerable E(n)-equivariant message passing on simplicial complexes. Our method integrates the expressivity of Clifford group-equivariant layers with …
View article: Designing Long-term Group Fair Policies in Dynamical Systems
Designing Long-term Group Fair Policies in Dynamical Systems Open
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 consi…
View article: Early-Exit Neural Networks with Nested Prediction Sets
Early-Exit Neural Networks with Nested Prediction Sets Open
Early-exit neural networks (EENNs) enable adaptive and efficient inference by providing predictions at multiple stages during the forward pass. In safety-critical applications, these predictions are meaningful only when accompanied by reli…
View article: Deep anytime-valid hypothesis testing
Deep anytime-valid hypothesis testing Open
We propose a general framework for constructing powerful, sequential hypothesis tests for a large class of nonparametric testing problems. The null hypothesis for these problems is defined in an abstract form using the action of two known …
View article: Lie Group Decompositions for Equivariant Neural Networks
Lie Group Decompositions for Equivariant Neural Networks Open
Invariance and equivariance to geometrical transformations have proven to be very useful inductive biases when training (convolutional) neural network models, especially in the low-data regime. Much work has focused on the case where the s…
View article: Simulation-based Inference with the Generalized Kullback-Leibler Divergence
Simulation-based Inference with the Generalized Kullback-Leibler Divergence Open
In Simulation-based Inference, the goal is to solve the inverse problem when the likelihood is only known implicitly. Neural Posterior Estimation commonly fits a normalized density estimator as a surrogate model for the posterior. This for…
View article: Latent Representation and Simulation of Markov Processes via Time-Lagged Information Bottleneck
Latent Representation and Simulation of Markov Processes via Time-Lagged Information Bottleneck Open
Markov processes are widely used mathematical models for describing dynamic systems in various fields. However, accurately simulating large-scale systems at long time scales is computationally expensive due to the short time steps required…
View article: Deep Gaussian Markov Random Fields for Graph-Structured Dynamical Systems
Deep Gaussian Markov Random Fields for Graph-Structured Dynamical Systems Open
Probabilistic inference in high-dimensional state-space models is computationally challenging. For many spatiotemporal systems, however, prior knowledge about the dependency structure of state variables is available. We leverage this struc…
View article: On the Effectiveness of Hybrid Mutual Information Estimation
On the Effectiveness of Hybrid Mutual Information Estimation Open
Estimating the mutual information from samples from a joint distribution is a challenging problem in both science and engineering. In this work, we realize a variational bound that generalizes both discriminative and generative approaches.…
View article: Clifford Group Equivariant Neural Networks
Clifford Group Equivariant Neural Networks Open
We introduce Clifford Group Equivariant Neural Networks: a novel approach for constructing $\mathrm{O}(n)$- and $\mathrm{E}(n)$-equivariant models. We identify and study the $\textit{Clifford group}$, a subgroup inside the Clifford algebra…
View article: Balancing Simulation-based Inference for Conservative Posteriors
Balancing Simulation-based Inference for Conservative Posteriors Open
Conservative inference is a major concern in simulation-based inference. It has been shown that commonly used algorithms can produce overconfident posterior approximations. Balancing has empirically proven to be an effective way to mitigat…
View article: Closed-loop automatic gradient design for liquid chromatography using Bayesian optimization
Closed-loop automatic gradient design for liquid chromatography using Bayesian optimization Open
Contemporary complex samples require sophisticated methods for full analysis. This work describes the development of a Bayesian optimization algorithm for automated and unsupervised development of gradient programs. The algorithm was tailo…
View article: Closed-loop automatic gradient design for liquid chromatography using Bayesian optimization
Closed-loop automatic gradient design for liquid chromatography using Bayesian optimization Open
Contemporary complex samples require sophisticated methods for full analysis. This work describes the development of a Bayesian optimization algorithm for automated and unsupervised development of gradient programs. The algorithm was tailo…
View article: Normalizing Flows for Hierarchical Bayesian Analysis: A Gravitational Wave Population Study
Normalizing Flows for Hierarchical Bayesian Analysis: A Gravitational Wave Population Study Open
We propose parameterizing the population distribution of the gravitational wave population modeling framework (Hierarchical Bayesian Analysis) with a normalizing flow. We first demonstrate the merit of this method on illustrative experimen…