arXiv Statistics ML
Minimax Rates for Conditional Generative Learning under Wasserstein Loss
Read the original on arXiv Statistics ML →The Flow has not summarised this story yet — read it at arXiv Statistics ML.
Related stories
arXiv Machine Learning
Jun 18
Wasserstein Policy Learning for Distributional Outcomes
arXiv:2606. 19117v1 Announce Type: cross Abstract: Offline policy learning has received growing attention in causal inference.
arXiv Machine Learning
Jun 2
Theoretical Analysis of Engression and Reverse Markov Engression
arXiv:2606. 01002v1 Announce Type: cross Abstract: Engression is a recently proposed and effective framework for conditional distribution learning.
arXiv Machine Learning
Sep 24
Robustness of Diffusion Models under Distribution Shift
arXiv:2609.27546v1 Announce Type: cross Abstract: Score-based diffusion models are increasingly considered in settings where the underlying data distribution may differ from the training distribution...
arXiv Statistics ML
1d ago
On the Error Analysis of Triangular Transport Maps for Conditional Generation via MMD-based Objectives
arXiv:2610.33610v1 Announce Type: new Abstract: Conditional generative models parameterized by triangular transport maps are widely used for conditional sampling, yet theoretical guarantees on the qu...
arXiv Machine Learning
6d ago
Near Minimax Rate for Quantile Distributional Reinforcement Learning
The paper investigates quantile distributional policy evaluation by approximating the return distribution under a policy with a quantile Bellman fixed point. It constructs an estimator from an empirical Markov decision process and derives non‑asymptotic error bounds in Wasserstein distances, achieving root‑n rates that are independent of the quantile resolution for a wide range of Wasserstein orders. The authors also characterize the exact local asymptotic minimax risk and show that their estimator attains this optimal rate, while examining how the risk depends on resolution in simple state‑space examples.
arXiv Statistics ML
Oct 16
Optimal score function estimation via derivatives constraints
The paper develops a statistical framework showing that empirical score matching can achieve minimax optimal performance for diffusion generative models when data lie on a low‑dimensional manifold. It establishes convergence rates for empirical risk minimization over constrained Sobolev classes and demonstrates that the resulting score estimators yield minimax optimal Wasserstein‑1 rates for the generated distribution, up to logarithmic factors. The analysis reveals that the statistical rates depend on the intrinsic dimension of the data manifold rather than its ambient dimension, providing conditions under which score‑based generative modeling generalizes rather than overfits.