BayesSum uses Gaussian processes to efficiently estimate expectations in discrete spaces, reducing sample requirements by over 50%.

Sophia Seulkee Kang, François-Xavier Briol, Toni Karvonen et al.

DoFlow employs continuous normalizing flows (CNF) integrated with causal DAGs for observational, interventional, and counterfactual time-series forecasting.

Dongze Wu, Feng Qiu, Yao Xie

This work proves that a Transformer with nonlinear MLP is asymptotically equivalent to a polynomial predictor, highlighting data quality and mixing effects on ICL.

Samet Demir, Zafer Dogan

Using singular learning theory to extend the minimum description length principle, this study finds local learning coefficient closely correlates with neural network compressibility.

Einar Urdshals, Edmund Lau, Jesse Hoogland et al.

Proposes an information-theoretic framework using predictive information and learning curves to assess the inherent learnability of sequential data.

Mario Morawski, Anais Despres, Rémi Rehm

Proposes innovations-representation-based TS-GPT for engineering time series, improving causal modeling and probabilistic forecasting.

Lang Tong, Xinyi Wang

Combining test-time training (TTT) with in-context learning (ICL), this work achieves low prediction risk for nonlinear single-index models, with error approaching noise levels as data grows.

Kento Kuwataka, Taiji Suzuki

Proposes a kernel-based stochastic approximation framework for nonlinear operator learning in infinite-dimensional spaces, with dimension-free convergence guarantees.

Jia-Qi Yang, Lei Shi

Introduced Conic Gromov-Wasserstein (CGW) distance for comparing unbalanced measure networks and hypernetworks, offering robustness and scalability.

Mary Chriselda Antony Oliver, Emmanuel Hartman, Tom Needham

Introduces non-asymptotic convergence bounds for conditional diffusion models using Wasserstein distance, integrating pre-trained functions for precise distribution approximation.

Mengze Li

Using random matrix theory, the paper compares asymptotic performance of Stack-SVD and SVD-Stack in high-dimensional data integration.

Tavor Z. Baharav, Phillip B. Nicol, Rafael A. Irizarry et al.

This paper introduces a posterior sampling-based expected improvement method, significantly reducing cumulative regret in Bayesian optimization.

Shion Takeno, Yu Inatsu, Masayuki Karasuyama et al.

Proposes ACE estimator leveraging higher-order cumulants for robust causal effect estimation under non-Gaussian noise, outperforming DML.

Jikai Jin, Lester Mackey, Vasilis Syrgkanis

Proposes doubly robust counterfactual policy mean embeddings (CPME) for flexible, nonparametric distribution estimation and hypothesis testing, outperforming existing methods.

Houssam Zenati, Bariscan Bozkurt, Arthur Gretton

This work introduces a low-dimensional subspace analysis to explain out-of-distribution generalization in in-context learning, showing task diversity enhances robustness.

Soo Min Kwon, Alec S. Xu, Can Yaras et al.

Reformulates Expected Free Energy planning as variational inference, integrating goal and information gain, enabling scalable resource-aware decision-making.

Bert de Vries, Wouter Nuijten, Thijs van de Laar et al.

Proposes scalable Sinkhorn-based algorithms for regularized OT linear models supporting various penalties and loss functions.

Tomasz Kacprzak, Francois Kamper, Michael W. Heiss et al.

Multi-variable batch Bayesian optimization in materials research analyzes noise sensitivity and problem landscape effects.

Imon Mia, Armi Tiihonen, Anna Ernst et al.

Proposes an optimization-based multivariate conformal set with minimal volume, ensuring finite-sample coverage.

Sacha Braun, Liviu Aolaritei, Michael I. Jordan et al.

Introduces conformal e-prediction using E-values and Ville’s inequality for flexible, non-exchangeable, sequential coverage guarantees.

Etienne Gauthier, Francis Bach, Michael I. Jordan