Výsledky vyhledávání

Report

ClassContrast: Bridging the Spatial and Contextual Gaps for Node Representations

Autor: Uddin, Md Joshem, Tola, Astrit, Sikand, Varin, Akcora, Cuneyt Gurcan, Coskunuzer, Baris

Graph Neural Networks (GNNs) have revolutionized the domain of graph representation learning by utilizing neighborhood aggregation schemes in many popular architectures, such as message passing graph neural networks (MPGNNs). This scheme involves ite

Externí odkaz: http://arxiv.org/abs/2410.02158

Zobrazit plný text záznamu

Report

New gravity field of comet 67P/C-G based on Rosetta's Doppler and optical data

Autor: Laurent-Varin, Julien, James, Théo, Marty, Jean-Charles, Jorda, Laurent, Maistre, Sebastien Le, Gaskell, Robert

We provide a new gravity field of Comet 67P-C/G up to degree 4. We detect mass heterogeneity in the comet nucleus. The loss of mass is restimated at 0.28\% of the comet's total mass (3 times larger than previous estimate). Comparison of the gravity f

Externí odkaz: http://arxiv.org/abs/2409.02692

Zobrazit plný text záznamu

Report

Tractable Ridge Regression for Paired Comparisons

Autor: Varin, Cristiano, Firth, David

Paired comparison models, such as Bradley-Terry and Thurstone-Mosteller, are commonly used to estimate relative strengths of pairwise compared items in tournament-style data. We discuss estimation of paired comparison models with a ridge penalty. A n

Externí odkaz: http://arxiv.org/abs/2406.09597

Zobrazit plný text záznamu

Report

The golf model on $\mathbb{Z}/n\mathbb{Z}$ and on $\mathbb{Z}$

Autor: Varin, Zoé

We introduce a particle model, that we call the $\textit{golf model}$. Initially, on a graph $G$, balls and holes are placed at random on some distinct vertices. Balls then move one by one, doing a random walk on $G$, starting from their initial vert

Externí odkaz: http://arxiv.org/abs/2401.13380

Zobrazit plný text záznamu

Report

Consistent and Scalable Composite Likelihood Estimation of Probit Models with Crossed Random Effects

Autor: Bellio, Ruggero, Ghosh, Swarnadip, Owen, Art B., Varin, Cristiano

Estimation of crossed random effects models commonly require computational costs that grow faster than linearly in the sample size $N$, often as fast as $\Omega(N^{3/2})$, making them unsuitable for large data sets. For non-Gaussian responses, integr

Externí odkaz: http://arxiv.org/abs/2308.15681

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání