arXiv:2511. 18945v4 Announce Type: replace Abstract: We propose a fully data-driven approach to designing mutual information (MI) estimators.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.
ALICE is a foundation model that estimates mutual information (MI) without per‑distribution training. Trained only on synthetic distributions, it acts as an in‑context estimator of rectified‑flow velocity fields, producing MI via a fixed identity that integrates squared differences between joint and conditional fields. The authors validate ALICE on a challenging benchmark and demonstrate its applicability to unseen data in biology, genetics, and neuroscience, achieving performance comparable to neural estimators trained separately for each distribution.
arXiv:2606. 25188v1 Announce Type: new Abstract: Efficient uncertainty quantification (UQ) is essential for trustworthy large-scale learning.
arXiv:2603.05575v2 Announce Type: replace-cross Abstract: We study prediction-powered conditional inference in the setting where labeled data are scarce, unlabeled covariates are abundant, and a blac...
arXiv:2606. 00241v1 Announce Type: cross Abstract: Measuring statistical dependency between high-dimensional random variables is a fundamental task in data science and machine learning.
arXiv:2605. 04847v2 Announce Type: replace-cross Abstract: Uncertainty quantification (UQ) in graph neural networks (GNNs) is crucial in high-stakes domains but remains a significant challenge.
The paper introduces DUO, a framework for Deep Imbalanced Regression that models each prediction as a conditional Gaussian to capture instance‑level uncertainty. By decoupling mean and variance optimization, DUO enhances learning signals for tail samples and mitigates gradient coupling that hampers hard examples. A distribution‑guided contrastive learning component further refines feature representations, leading to state‑of‑the‑art performance on several visual and biological regression benchmarks.