9 papers
Variational Learning for Insertion-based Generation
Yangtian Zhang, Zhe Wang, Arthur Gretton +4
Non-monotonic sequence generation methods, such as masked diffusion models, provide a flexible alternative to left-to-right autoregressive modeling by allowing tokens to be generat…
On the Wasserstein Gradient Flow Interpretation of Drifting Models
Arthur Gretton, Li Kevin Wenliang, Alexandre Galashov +3
Recently, Deng et al. (2026) proposed Generative Modeling via Drifting (GMD), a novel framework for generative tasks. This note presents an analysis of GMD through the lens of Wass…
Sobolev Regularized MMD Gradient Flow
Chenyang Tian, Bharath K. Sriperumbudur, Arthur Gretton +1
We propose Sobolev-regularized Maximum Mean Discrepancy (SrMMD) gradient flow, a regularized variant of maximum mean discrepancy (MMD) gradient flow based on a gradient penalty on…
Doubly Robust Proxy Causal Learning with Neural Mean Embeddings
Bariscan Bozkurt, Alexandre Galashov, Dimitri Meunier +3
Unobserved confounding prevents standard covariate adjustment from identifying causal response functions in observational studies. Proxy causal learning addresses this problem thro…
Closed-Form Last Layer Optimization
Alexandre Galashov, Nathaël Da Costa, Liyuan Xu +2
Neural networks are typically optimized with variants of stochastic gradient descent. Under a squared loss, however, the optimal solution to the linear last layer weights is known…
Fast Best-in-Class Regret for Contextual Bandits
Samuel Girard, Aurelien Bibaut, Arthur Gretton +2
We study the problem of stochastic contextual bandits in the agnostic setting, where the goal is to compete with the best policy in a given class without assuming realizability or…