Arthur Gretton

Learn to Guide Your Diffusion Model

Closed-form Last Layer Optimization

Outcome-Aware Spectral Feature Learning for Instrumental Variable Regression

LO-ARMs++: Improving Learning-Order Autoregressive Models for Molecular String Generation

Regularized least squares learning with heavy-tailed noise is minimax optimal

On the Hardness of Conditional Independence Testing In Practice

Distributional Diffusion Models with Scoring Rules

Demystifying Spectral Feature Learning for Instrumental Variable Regression

Density Ratio-Free Doubly Robust Proxy Causal Learning

Doubly-Robust Estimation of Counterfactual Policy Mean Embeddings

Optimality and Adaptivity of Deep Neural Features for Instrumental Variable Regression

Accelerated Diffusion Models via Speculative Sampling

Learning-Order Autoregressive Models with Application to Molecular Graph Generation

Deep MMD Gradient Flow without adversarial training