Zobrazeno 1 - 10
of 498
pro vyhledávání: '"Forré, P."'
We show that for a given DAG $G$, among all observational distributions of Bayesian networks over $G$ with arbitrary outcome spaces, the faithful distributions are `typical': they constitute a dense, open set with respect to the total variation metri
Externí odkaz:
http://arxiv.org/abs/2410.16004
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 correlations,
Externí odkaz:
http://arxiv.org/abs/2409.19991
Publikováno v:
AI for Science Workshop at the 41st International Conference on Machine Learning (ICML), 2024
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 model of contin
Externí odkaz:
http://arxiv.org/abs/2407.10259
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 vanish. Rece
Externí odkaz:
http://arxiv.org/abs/2407.02134
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 on the tra
Externí odkaz:
http://arxiv.org/abs/2406.15753
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 neural net
Externí odkaz:
http://arxiv.org/abs/2406.04052
Autor:
Zhdanov, Maksim, Ruhe, David, Weiler, Maurice, Lucic, Ana, Brandstetter, Johannes, Forré, Patrick
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, $\mathrm{E}(3)$-e
Externí odkaz:
http://arxiv.org/abs/2402.14730
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 simplicial
Externí odkaz:
http://arxiv.org/abs/2402.10011
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 w
Externí odkaz:
http://arxiv.org/abs/2311.12447
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 reliable uncert
Externí odkaz:
http://arxiv.org/abs/2311.05931