arXiv:2510.02499v1 Announce Type: new Abstract: Diffusion models have emerged as powerful generative frameworks with widespread applications across machine learning and artificial intelligence systems. While current research has predominantly focused on linear diffusions, these approaches can face significant challenges when modeling…
arXiv:2412.09235v2 Announce Type: replace-cross Abstract: We study stability of optimizers and convergence of Sinkhorn’s algorithm for the entropic optimal transport problem. In the special case of the quadratic cost, our stability bounds imply that if one of the two entropic…
arXiv:2510.02702v1 Announce Type: cross Abstract: Understanding how urban residents travel between neighborhoods and destinations is critical for transportation planning, mobility management, and public health. By mining historical origin-to-destination flow patterns with spatial, temporal, and functional relations among urban places, we…
arXiv:2510.02721v1 Announce Type: cross Abstract: Hyperparameters greatly impact models’ capabilities; however, modern models are too large for extensive search. Instead, researchers design recipes that train well across scales based on their understanding of the hyperparameters. Despite this importance, few tools…
arXiv:2505.13564v2 Announce Type: replace-cross Abstract: Decision-focused learning (DFL) is an increasingly popular paradigm for training predictive models whose outputs are used in decision-making tasks. Instead of merely optimizing for predictive accuracy, DFL trains models to directly minimize the loss associated…
arXiv:2510.03021v1 Announce Type: cross Abstract: The Wasserstein barycenter is defined as the mean of a set of probability measures under the optimal transport metric, and has numerous applications spanning machine learning, statistics, and computer graphics. In practice these input measures…
arXiv:2407.17446v2 Announce Type: replace Abstract: In this paper, we propose a novel generalisation of the signature of a path, motivated by fractional calculus, which is able to describe the solutions of linear Caputo controlled FDEs. We also propose another generalisation…
arXiv:2510.03056v1 Announce Type: cross Abstract: Chaos expansions are widely used in global sensitivity analysis (GSA), as they leverage orthogonal bases of L2 spaces to efficiently compute Sobol’ indices, particularly in data-scarce settings. When derivatives are available, we argue that a…
arXiv:2505.08277v2 Announce Type: replace Abstract: The impressive practical performance of neural networks is often attributed to their ability to learn low-dimensional data representations and hierarchical structure directly from data. In this work, we argue that these two phenomena are not…
arXiv:2510.03109v1 Announce Type: cross Abstract: We prove rates of convergence and robustness to prior misspecification within a Generalised Variational Inference (GVI) framework with bounded divergences. This addresses a significant open challenge for GVI and Federated GVI that employ a different…
