Proposed an active sampling flow using sensitivity analysis and Bayesian surrogate modeling to enhance analog circuit simulation efficiency.

Reda Chhaibi, Fabrice Gamboa, Christophe Oger et al.

Unified data-dependent generalization bounds via PAC-Bayesian on random sets, applied to fractal dimension and Langevin dynamics.

Benjamin Dupuis, Paul Viallard, George Deligiannidis et al.

Proposes neural network-enhanced kernel conditional mean embeddings for scalable, flexible conditional distribution modeling, outperforming existing methods in density estimation and reinforcement learning.

Eiki Shimizu, Kenji Fukumizu, Dino Sejdinovic

Introduces measure pre-conditioning via γ-convergence to enhance stability and convergence in parametric ML models and transfer learning.

Joaquín Sánchez García

ZOD-MC offers gradient-free sampling for non-log-concave distributions with polynomial convergence guarantees in low dimensions.

Ye He, Kevin Rojas, Molei Tao

Noiseless Kernel Ridge Regression (KRR) achieves minimax optimal rates, revealing super-smoothness effects and saturation phenomena based on eigenvalue decay and target smoothness.

Jihao Long, Xiaojun Peng, Lei Wu

Proposes LowPopArt for low-rank matrix estimation with experimental design, achieving tighter recovery guarantees.

Kyoungseok Jang, Chicheng Zhang, Kwang-Sung Jun

Introduced Discrete Flow Models (DFM) for multimodal generation, achieving state-of-the-art in protein co-design.

Andrew Campbell, Jason Yim, Regina Barzilay et al.

Introduces optimal Sobolev norm convergence rates for infinite-dimensional vector-valued ridge regression, removing boundedness assumptions via tensor product interpolation spaces.

Zhu Li, Dimitri Meunier, Mattes Mollenhauer et al.

RMIA introduces a low-cost, high-power membership inference attack using fine-grained likelihood ratio tests, outperforming prior methods.

Sajjad Zarifzadeh, Philippe Liu, Reza Shokri

Proposes leverage score-based sampling for RKHS numerical integration, reducing computational cost while maintaining optimal error rates.

Antoine Chatalic, Nicolas Schreuder, Ernesto De Vito et al.

Introduced a variable selection method using Maximum Mean Discrepancy for interpretable distribution comparison.

Kensuke Mitsuzawa, Motonobu Kanagawa, Stefano Bortoli et al.

Using determinantal point processes for signal reconstruction, providing $L^2$ mean-square guarantees and superconvergence phenomena.

Ayoub Belhadji, Rémi Bardenet, Pierre Chainais

Introduces Conformal Decision Theory with online risk calibration, ensuring provable low-risk decisions in adversarial environments; validated in robot navigation, manufacturing, and trading.

Jordan Lekeufack, Anastasios N. Angelopoulos, Andrea Bajcsy et al.

Introducing Quasi-Monte Carlo (QMC) methods to efficiently approximate 3D sliced Wasserstein distances with theoretical guarantees.

Khai Nguyen, Nicola Bariletto, Nhat Ho

Proposes convergence analysis for online vector-valued kernel regression, achieving order-optimal error bounds under noise and smoothness assumptions.

Michael Griebel, Peter Oswald

Kernel-based nonlinear meta-learning guarantees faster generalization rates in infinite-dimensional RKHS.

Dimitri Meunier, Zhu Li, Arthur Gretton et al.

Proposes Twisted Diffusion Sampler (TDS), combining SMC and twisting to achieve asymptotic exactness in conditional diffusion sampling, enhancing protein design and image generation.

Luhuan Wu, Brian L. Trippe, Christian A. Naesseth et al.

Estimate joint probability distribution using low-rank tensor decomposition and Radon transforms, significantly reducing sample complexity.

Pranava Singhal, Waqar Mirza, Ajit Rajwade et al.

Using dynamical mean field theory, this paper quantifies finite-width neural network kernel and prediction fluctuations, revealing how feature learning dynamically reduces variance.

Blake Bordelon, Cengiz Pehlevan