Graph neural networks are widely used for transductive node classification, with accuracy typically measured on randomly drawn train/validation/test splits. Reported accuracy has been shown to shift substantially across different random splits of the same dataset, making published comparisons between architectures unre...
Naga Venkata Sai Jitin Jami, Thomas R. Altstidl, S. Hoefler et al.· 0 citations
Experiments with GRPO and GiGPO on ALFWorld, WebShop, and SearchQA show that both axes provide independent gains and that their combi- nation consistently achieves the strongest overall performance across model scales.
Ying-Xuan Zhuang, Bin-He Yu, Jing-Xiao Yang et al.· 1 citation
The growing availability of multi-omics data and the rise of network-based and machine-learning methods have created both an opportunity and a challenge for the systems pharmacology community: the opportunity to model drug action at unprecedented mechanistic resolution at different scales, and the challenge of equippin...
Malvina Marku, The-Chuong Trinh, Racym Berrah et al.· Zenodo (CERN European Organi...· 1 citation
This paper studies the regret analysis for parallel Gaussian process (GP) bandit optimization. The known regret upper bounds for the widely used GP batched upper confidence bound and GP batched Thompson sampling (GP-BTS) suffer from a multiplicative factor with respect to the batch size $Q$. To avoid this degradation,...
Shion Takeno, Shogo Iwazaki· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Median-of-means (MoM) is a powerful technique that theoretically enables near sub-Gaussian finite-sample rate for parameter estimation when the underlying data distribution is heavy-tailed (e.g., assumed to have only two first finite moments). A recent work has extrapolated this technique to median-of-\textit{randomize...
This work uncovers variational principles behind symmetrizing the Bregman divergences induced by generic mirror maps over the cone of positive definite matrices. We show that computing the canonical means for this symmetrization can be posed as minimizing the desired symmetrized divergences over a set of mean functiona...
Accurately and efficiently estimating the variance of the Maximum Mean Discrepancy (MMD) remains challenging, particularly for unbalanced sample sizes. In this paper, we derive a finite-sample unbiased estimator of the MMD variance. To overcome the traditional $\mathcal{O}(N^2)$ computational bottleneck, we develop a r...
Shi-Jie Zhong, Yikun Yang, Da Gong et al.· 0 citations
Wasserstein-Fisher-Rao (WFR) gradient flows have been recently proposed as a powerful sampling tool that combines the advantages of pure Wasserstein (W) and pure Fisher-Rao (FR) gradient flows. Existing algorithmic developments implicitly make use of operator splitting techniques to numerically approximate the WFR part...
F. R. Crucinio, S. Pathiraja· arXiv.org· 2 citations
Solving ill-posed inverse problems requires powerful and flexible priors. We propose leveraging pretrained latent diffusion models for this task through a new training-free approach, termed Diffusion-regularized Wasserstein Gradient Flow (DWGF). Specifically, we formulate the posterior sampling problem as a Wasserstein...
A Bayesian inference framework using Sylvester normalizing flows (SNFs) to approximate posterior distributions over metabolite concentrations, enhancing quantification reliability, and a physics-based decoder incorporates prior knowledge of MRS signal formation, ensuring realistic distribution representations.
Julian P. Merkofer, D. V. D. van de Sande, A. Bhogal et al.· arXiv.org· 0 citations
Bayesian quadrature is a probabilistic, model-based approach to numerical integration, the estimation of intractable integrals, or expectations. Although Bayesian quadrature was popularized already in the 1980s, no systematic and comprehensive treatment has been published. The purpose of this survey is to fill this gap...
Maren Mahsereci, Toni Karvonen· Foundations and Trends in Ma...· 3 citations· ⚡1
A reconstruction-driven design density is derived and the posterior mean is used to build a training-free warp that places more measurements where the target function varies rapidly, and a geometric equalizer separately corrects boundary bias.
Sanna Jarl, Jens Sjölund, Jonathan J. S. Scragg et al.· 0 citations
Learn how Google DeepMind and GovTech Singapore uses lightweight on-device Gemma models to intercept conversational scams in private chats with zero cloud data egress.
MIT News · Artificial Intelligence· news.mit.eduOct 8, 2026
