Proposes a landing-based optimization method on Stiefel manifold with convergence rates matching Riemannian algorithms, avoiding costly projections.

Pierre Ablin, Simon Vary, Bin Gao et al.

Proposes Simplex Random Features (SimRFs) for optimal kernel approximation via geometric correlation, outperforming orthogonal RFs with minimal extra cost.

Isaac Reid, Krzysztof Choromanski, Valerii Likhosherstov et al.

Proposes Collider Regression, leveraging causal graph colliders to improve regression generalization via projection in RKHS.

Shahine Bouabid, Jake Fawkes, Dino Sejdinovic

Proposes doubly robust kernel statistics for testing distributional causal effects, combining counterfactual mean embeddings with permutation tests.

Jake Fawkes, Robert Hu, Robin J. Evans et al.

Unbalanced OT combined with entropic regularization and Gromov-Wasserstein enhances high-dimensional data matching robustness and efficiency.

Thibault Séjourné, Gabriel Peyré, François-Xavier Vialard

MALI leverages label-guided diffusion maps and optimal transport for manifold alignment, outperforming state-of-the-art methods.

Andres F. Duque, Myriam Lizotte, Guy Wolf et al.

This paper proves that two-layer neural networks trained with SGD converge their first-layer weights to the k-dimensional principal subspace spanned by the target model's index vectors, enabling low-dimensional feature learning.

Alireza Mousavi-Hosseini, Sejun Park, Manuela Girotti et al.

Proposed a data-adaptive kernel Bayesian method within computational graph framework for one-shot learning of SDEs, improving likelihood by 15% on benchmark models.

Matthieu Darcy, Boumediene Hamzi, Giulia Livieri et al.

Using moment relaxations and SOS proofs, this work establishes performance guarantees for outlier-robust geometric estimation in robotics and vision, effective even with high outlier ratios.

Luca Carlone

Introduces optimal learning rates for regularized conditional mean embedding under misspecification using a novel vector-valued interpolation space.

Zhu Li, Dimitri Meunier, Mattes Mollenhauer et al.

Introduces PPD to train CNFs on manifolds, avoiding ODE solving, enabling high-dimensional generation.

Heli Ben-Hamu, Samuel Cohen, Joey Bose et al.

Accelerate Sinkhorn algorithm using data-dependent initialization, boosting efficiency without loss of differentiability.

James Thornton, Marco Cuturi

Proposes a furthest-answer-based ε-optimal identification algorithm for linear bandits, reducing sample complexity near theoretical limits.

Marc Jourdan, Rémy Degenne

Proposes a continuous-time diffusion framework for discrete data using CTMCs, with Tau-leaping for efficient sampling, outperforming discrete methods.

Andrew Campbell, Joe Benton, Valentin De Bortoli et al.

Two-layer ReLU networks in teacher-student models outperform kernel methods, achieving near-global optimality at O(n^{-1}) rate.

Shunta Akiyama, Taiji Suzuki

Proposes an average-case error bound for kernel-based Bayesian quadrature using a two-step meta-algorithm, effective in noisy and randomized settings, especially with Matérn and SE kernels.

Xu Cai, Chi Thanh Lam, Jonathan Scarlett

Derived asymptotic differential equations describe how shallow nonlinear autoencoders sequentially learn principal components in high-dimensional data.

Maria Refinetti, Sebastian Goldt

Orthogonal polynomial-based DPP reduces gradient variance in SGD, achieving faster convergence.

Remi Bardenet, Subhro Ghosh, Meixia Lin

Neural Schrödinger-Föllmer flows enable finite-time, low-variance Bayesian inference in high dimensions via stochastic control and neural network parametrization.

Francisco Vargas, Andrius Ovsianas, David Fernandes et al.

Proposes tighter online confidence intervals for RKHS elements, reducing width growth from O(√γn) to near logarithmic, enhancing regret bounds.

Sattar Vakili, Jonathan Scarlett, Tara Javidi