Ribbon: Influence-function-based scalable approximation for Bayesian uncertainty, improving calibration and efficiency.

Graham Gibson, John Tipton, Kellin Rumsey et al.

This paper develops a theoretical framework for synthetic augmentation in score-based imbalanced classification, showing limited gains under well-specified models and potential improvements under model misspecification.

Zhengchi Ma, Pengfei Lyu, Anru R. Zhang

Proposes SSH-Net, a deep neural network integrated with cause-specific competing risks model, for failure time distribution prediction on GPU data, leveraging hierarchical data structures.

Jie Min, Yueyao Wang, Mengkun Chen

ProtoX-AD is a prototype-based self-explainable time series anomaly detection framework that achieves comparable performance to black-box models by leveraging transformation-aware latent representations.

Aitor Sánchez-Ferrera, Elisabeth Wetzer, Kristoffer Wickstrøm et al.

This paper introduces two calibration strategies—post-hoc calibration and in-training adaptation—for Bayesian prediction under label shift, validated through synthetic experiments.

Seungjin Choi

Introduces Itô maps for arbitrary-step SDE sampling, enabling conditional sampling and control, enhancing diversity and efficiency.

Zhengkai Pan, Peter Potaptchik, Wenxi Yao et al.

Proposes KDE-gradient conservative drifting with finite-particle convergence rates up to N^{-(2-β)/(2(d+4-β))}

Krishnakumar Balasubramanian

Proposed a model-based bootstrap method for finite controlled Markov chains, improving confidence interval coverage.

Ziwei Su, Imon Banerjee, Diego Klabjan

A divergence-based method outperforms traditional weighting in small sample scenarios.

Olav Benjamin Vassend

CLVAE model uses a variational autoencoder for long-term customer revenue forecasting, enhancing accuracy.

Jeffrey Näf, Riana Valera Mbelson, Markus Meierer

The Mixed Membership sub-Gaussian Model (MMSG) addresses the limitation of classical GMM by allowing observations to belong to multiple components.

Huan Qing

WassersteinGrad explains dynamic physical field predictions by computing the entropic Wasserstein barycenter, enhancing autoregressive weather forecasting model interpretability.

Younes Essafouri, Laure Raynaud, Luciano Drozda et al.

FedSPDnet outperforms traditional methods on EEG datasets using ProjAvg and RLAvg strategies, enhancing F1 score and robustness.

Thibault Pautrel, Florent Bouchard, Ammar Mian et al.

SQUEAK algorithm achieves low space complexity for kernel ridge regression using unnormalized ridge leverage scores.

Daniele Calandriello, Alessandro Lazaric, Michal Valko

Pliable Rejection Sampling (PRS) learns the proposal distribution using kernel estimation, ensuring high-probability i.i.d. sampling.

Akram Erraqabi, Michal Valko, Alexandra Carpentier et al.

Concave statistical utility maximization bandits using influence-function gradients.

Matías Carrasco, Alejandro Cholaquidis

Fast estimation of Gaussian mixture components via centering and singular value thresholding without iteration.

Huan Qing

Revisiting active sequential prediction-powered mean estimation reveals smallest confidence width when constant probability weight is near one.

Maria-Eleni Sfyraki, Jun-Kun Wang

Introduced spectral bandit algorithms for smooth graph functions, achieving linear and sublinear scaling in effective dimension.

Michal Valko, Rémi Munos, Branislav Kveton et al.

Adaptive kernel selection enhances stability and accuracy of kernelized diffusion maps.

Othmane Aboussaad, Adam Miraoui, Boumediene Hamzi et al.