Background Autism Spectrum Disorder (ASD) is a neurodevelopmental condition characterized by impairments in social communication and restricted or repetitive behaviours. Early diagnosis is important for timely intervention, motivating increasing interest in computer-aided diagnostic systems based on neuroimaging data....
Sneha Nayak, Anjan Gudigar, R. U. et al.· F1000Research· 0 citations
CUSP makes magnitude, timing, mechanism, movement, modes, and textual evidence compatible views of one lexical history compatible with a large corpus of US court opinions.
The quadrature field is introduced, a set-equivariant network that maps an observation and its posterior samples to an $M$-node signed-weight quadrature in one forward pass and is validated on closed-form and on learned posteriors, where it improves on the Monte-Carlo estimate in median at every node count, often by or...
Unobserved confounding is a key challenge when estimating causal effects from a treatment on an outcome. In this work, we assume that we observe a single, potentially multi-dimensional proxy variable of the unobserved confounder and that we know the mechanism that generates the proxy from the confounder. Under an assum...
Silvan Vollmer, Niklas Pfister, Sebastian Weichwald· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
This work develops a mathematical framework based on probability and optimal transport that provides a mathematical characterization of the expressive power of Transformers for contextual relations and shows how the choice of normalization determines the probabilistic structure of the relations represented by attention...
This work introduces latent subspaces in the exponential parameter space of product manifolds of categorical distributions as a novel approach to learning low-dimensional representations of high-dimensional discrete data.
Daniel Gonzalez-Alvarado, Jonas Cassel, Stefania Petra et al.· arXiv.org· 0 citations
This work considers a class of statistical inverse problems involving the estimation of a regression operator from a Polish space to a separable Hilbert space, where the target lies in a vector-valued reproducing kernel Hilbert space induced by an operator-valued kernel.
Federated Bayesian neural networks require fixing a prior on the model parameters, which is notoriously difficult, and misspecification of this prior can severely degrade accuracy and calibration. Motivated by the rapid progress of predictive models, the martingale posterior, also known as predictive Bayes, replaces th...
Boning Zhang, Matteo Zecchin, Mingzhao Guo et al.· 0 citations
Interactive decision making is the problem of learning to act well in an unknown environment, using the data that one's own actions generate to continuously improve, and arises in situations ranging from online platforms and robotics to medical treatments. This monograph gives a statistical perspective on algorithm des...
Recent literature has shown a strong connection between optimization and sampling. We develop the corresponding first-order theory for diffusion models. First, the SDE-based reverse-time flows of overdamped and underdamped Langevin diffusions contract relative Fisher divergences at explicit exponential rates whenever t...
A simulation-based inference framework for rough Heston (rHeston) calibration that learns the posterior distribution of the model parameters conditional on an IV surface and introduces Hellinger-SHAP, an information-theoretic explainability method for posterior inference.
Outliers are essential for evaluating and improving the robustness of machine learning systems, especially when future distributions may differ significantly from historical training data. In high-stakes applications, robustness often depends on rare cases that finite datasets fail to capture, making simple resampling...
Jennifer Neville did not want to go into computer science—but that’s exactly where she landed. Neville discusses the starts and stops that led to her professional sweet spot and her work identifying “surprising failures” making it hard for AI to handle complexity. The post What AI gets wrong and what failure teaches us appeared first on Microsoft Research.
