Introduces Prediction-Powered Smoothing (PP-S) and validation methods to enhance accuracy in disaggregated AI evaluation.

Sho Kawano, Zehang Richard Li, Paul A. Parker

Study TAP approximation accuracy in spherical linear models, finding errors below fluctuation scale.

Jingbo Liu, Zhiyuan Yu

OKSPCA combines random features and Adam update for supervised dimension reduction, showing pipeline-dependent performance across six benchmarks.

Zhenlin Yao, Wei Xiong

The paper proposes PAC-Bayesian reconstruction guarantees for time series VAEs, capturing temporal dependencies.

Chloé Hashimoto-Cullen, Ghislain Agoua, Benjamin Guedj et al.

FluxDisco uses Monte Carlo Graph Search for symbolic regression in stoichiometric dynamical systems, ensuring physical adherence.

Cassandra Durr, Alvaro Köhn-Luque, Chris Jewell et al.

Study shows pooling dependent samples in self-supervised learning is more effective than partitioning independent samples.

Maximilian Fleissner, Debarghya Ghoshdastidar, Samory Kpotufe

The paper proposes a diffusion-based method for estimating local intrinsic dimension with a minimax lower bound.

Jaehee Seo, Wontae Jeong, Jisu Kim

ALRA improves distillation efficiency via adaptive local relational alignment, boosting accuracy by 2.91 points on The Pile zero-shot benchmarks.

Quang Hoang Trung, Quang Huu Hieu, Nguyen Van Hoang Phuc et al.

OQRC uses finite occupancy to tighten finite-sample quantile-risk control, cutting MS COCO RiskGap by 78.64%.

Zihao Shi, Huajun Xi, Bingyi Jing et al.

Provides sharp asymptotic analysis of kernel ridge regression under power-law anisotropic Gaussian data, revealing how input geometry shapes learning curves and generalization.

Lorenzo Rizzi, Arie Wortsman Zurich, Bruno Loureiro

I-FLOP is a fast causal structure learning algorithm from interventional data, leveraging target-filtered BIC scores with theoretical consistency guarantees.

Liuting Chen, Alex Markham

Proposes OCE-based risk-averse decision-making with prediction sets for high-probability risk control, validated in wireless beamforming.

Amirmohammad Farzaneh, Osvaldo Simeone

Using critic-sourced artist relations and 80 acoustic features with Wasserstein distance, the study validates their musical similarity (AUC 0.767)

Elena Badillo-Goicoechea, Fengfeng He

Proposes Primal–Dual neural framework for timely classification, balancing sensitivity, specificity, and monitoring costs with guarantees.

Jiaming Qiu, Yingye Zheng, Ying-Qi Zhao

Introduces the Exceedance Design Effect to correct clustering bias in threshold-based conformal prediction, improving effective sample size estimates.

Adam Noonan

Analytical and particle-based methods for uncertainty propagation in random neural networks using Leaky ReLU's piecewise linearity, extended to autonomous dynamical systems.

Janice Adams, Daniele Venturi

Proposes a transfer learning framework using deep ReLU networks for nonparametric regression, achieving near-minimax convergence rates in high-dimensional settings.

Junpeng Ren, Carlos Misael Madrid Padilla, Yanzhen Chen et al.

Nested SMC enhances discrete diffusion inference control, outperforming traditional methods with significant improvements.

Lohithsai Yadala Chanchu, Hany Abdulsamad, Christian A. Naesseth

Proposes density-reweighted entropic OT to decouple geometry from sampling density, improving alignment fidelity on low-dimensional manifolds with density disparities.

Keyi Li, Yuval Kluger, Boris Landa

Proposes online inference in distributional TD learning, establishing weak convergence to Gaussian processes and bootstrap consistency for smooth and nonsmooth functionals.

Yang Peng, Liangyu Zhang