Archives AI News

Singleton-Optimized Conformal Prediction

arXiv:2509.24095v1 Announce Type: new Abstract: Conformal prediction can be used to construct prediction sets that cover the true outcome with a desired probability, but can sometimes lead to large prediction sets that are costly in practice. The most useful outcome…

DAL: A Practical Prior-Free Black-Box Framework for Non-Stationary Bandits

arXiv:2501.19401v4 Announce Type: replace-cross Abstract: We introduce a practical, black-box framework termed Detection Augmented Learning (DAL) for the problem of non-stationary bandits without prior knowledge of the underlying non-stationarity. DAL accepts any stationary bandit algorithm as input and augments it…

Precise Asymptotics of Bagging Regularized M-estimators

arXiv:2409.15252v3 Announce Type: replace-cross Abstract: We characterize the squared prediction risk of ensemble estimators obtained through subagging (subsample bootstrap aggregating) regularized M-estimators and construct a consistent estimator for the risk. Specifically, we consider a heterogeneous collection of $M ge 1$…

End-to-End Deep Learning for Predicting Metric Space-Valued Outputs

arXiv:2509.23544v1 Announce Type: new Abstract: Many modern applications involve predicting structured, non-Euclidean outputs such as probability distributions, networks, and symmetric positive-definite matrices. These outputs are naturally modeled as elements of general metric spaces, where classical regression techniques that rely on…

Flow Matching for Robust Simulation-Based Inference under Model Misspecification

arXiv:2509.23385v1 Announce Type: new Abstract: Simulation-based inference (SBI) is transforming experimental sciences by enabling parameter estimation in complex non-linear models from simulated data. A persistent challenge, however, is model misspecification: simulators are only approximations of reality, and mismatches between simulated…

A Unified Information-Theoretic Framework for Meta-Learning Generalization

arXiv:2501.15559v2 Announce Type: replace Abstract: In recent years, information-theoretic generalization bounds have gained increasing attention for analyzing the generalization capabilities of meta-learning algorithms. However, existing results are confined to two-step bounds, failing to provide a sharper characterization of the meta-generalization…

A Generative Model for Controllable Feature Heterophily in Graphs

arXiv:2509.23230v1 Announce Type: new Abstract: We introduce a principled generative framework for graph signals that enables explicit control of feature heterophily, a key property underlying the effectiveness of graph learning methods. Our model combines a Lipschitz graphon-based random graph generator…