The paper extends Neural Posterior Estimation (NPE) to handle simulators whose parameter spaces contain both discrete and continuous dimensions. It introduces an inference network that factorizes the joint posterior into discrete and continuous components, using an autoregressive classifier for the discrete part and a generative model for the continuous part, trained jointly with a single simulation-based objective. A diagnostic tool for assessing calibration of the mixed posterior is also proposed, and the method is shown to produce accurate, calibrated posteriors on toy and real scientific simulators.
By Jan Boelts, Cornelius Schr\"oder, Jonas Beck, Jakob H. Macke, Michael Deistler, Daniel Gedon
arXiv:2608. 05930v1 Announce Type: cross Abstract: The experience sampling method (ESM) is a longitudinal research design where participants report their thoughts, emotional states and behaviours multiple times a day.
By Nina van Gerwen, Dimitris Rizopoulos, Manon Hillegers, Loes Keijsers, Sten Willemsen
The paper introduces a scalable Variational Expectation Maximization (VEM) algorithm for fitting large Nonlinear Mixed Effects (NLME) models, addressing computational challenges that arise as parameter and random‑effect counts grow. VEM leverages flexible variational families and reverse‑mode automatic differentiation to efficiently maximize the marginal likelihood, enabling fitting of models with over 15,000 population parameters. Experiments using the Pumas software demonstrate VEM’s ability to improve log‑likelihood over many iterations while remaining computationally feasible, whereas traditional FOCE methods fail to complete even a single iteration for similarly sized models.
By Mohamed Tarek, Pedro Afonso
arXiv:2605. 09075v2 Announce Type: replace-cross Abstract: Although the Laplace approximation offers a simple route to uncertainty quantification in deep neural networks, its reliance on inverting large Hessian matrices has motivated a range of computationally feasible low-dimensional or sparse approximations.
By Swarnali Raha, Kshitij Khare, Rohit K Patra
arXiv:2503. 10496v2 Announce Type: replace-cross Abstract: Modeling natural phenomena with artificial neural networks (ANNs) often provides highly accurate predictions.
By Eirik H{\o}yheim, Lars Skaaret-Lund, Solve S{\ae}b{\o}, Aliaksandr Hubin
arXiv:2608. 06107v1 Announce Type: new Abstract: Machine learning offers a promising avenue to accelerate physical simulations by replacing computationally expensive traditional Partial Differential Equation (PDE) solvers with fast, differentiable surrogate models.
By Guillaume Couairon, Alexis Jacq, Yu-Han Wu, Renu Singh, Yana Hasson, Quentin Berthet, Romuald Elie
arXiv:2606. 29951v1 Announce Type: new Abstract: Interpretable Mesomorphic Neural Networks (IMNs) offer a promising framework that combines the predictive power of deep neural networks with the interpretability of linear models.
By Hugo L. Hammer, Vajira Thambawita, Kristoffer Herland Hellton, P{\aa}l Halvorsen
arXiv:2607. 12570v1 Announce Type: cross Abstract: Multiscale problems are notoriously difficult to tackle using traditional numerical methods, as accurately resolving fine-scale features often requires prohibitively fine discretizations.
By Marc Haltmayer, Jaemin Seo, Yuseung Lee, Sungyeop Lee, Jaehoon Jeong, Jae Yong Lee
arXiv:2606. 06861v1 Announce Type: cross Abstract: Understanding nonlinear feature interactions is crucial in science and engineering, yet standard multilayer perceptrons (MLPs) often capture such interactions only implicitly, leading to entangled representations that can impair robustness and interpretability.
By Ziyuan Li, Uwe Jaekel, Babette Dellen
arXiv:2603.20111v2 Announce Type: replace
Abstract: The Joint-Embedding Predictive Architecture (JEPA) is often seen as a non-generative alternative to likelihood-based self-supervised learning, emph...
By Moritz G\"ogl, Christopher Yau
arXiv:2607. 10803v1 Announce Type: cross Abstract: Understanding which parameters are influential in Large Language Models (LLMs) is central to improving their efficiency, reliability, and interpretability.
By Shrestha Datta, Hongfu Liu, Anshuman Chhabra
Neural Composite Likelihood Estimation (NCLE) extends simulation‑based inference to high‑dimensional time series by partitioning long sequences into equal‑sized batches. For each batch, a neural network estimates the likelihood via conditional density estimation, and the product of these batch likelihoods forms an approximate composite likelihood. Frequentist inference is then performed by maximizing this composite likelihood to obtain a point estimate and by estimating the Godambe information matrix to derive confidence intervals.
By Grace Yan, Mark Beaumont, Dennis Prangle