5 papers
Latent Nonlinear Denoising Score Matching for Enhanced Learning of Structured Distributions
Kaichen Shen, Wei Zhu
We present latent nonlinear denoising score matching (LNDSM), a novel training objective for score-based generative models that integrates nonlinear forward dynamics with the VAE-b…
Sample-efficient quantum error mitigation via classical learning surrogates
Wei-You Liao, Ge Yan, Yujin Song +5
The pursuit of practical quantum utility on near-term quantum processors is critically challenged by their inherent noise. Quantum error mitigation (QEM) techniques are leading sol…
Statistical Learning Guarantees for Group-Invariant Barron Functions
Yahong Yang, Wei Zhu
We investigate the generalization error of group-invariant neural networks within the Barron framework. Our analysis shows that incorporating group-invariant structures introduces…
Robust Generative Learning with Lipschitz-Regularized -Divergences Allows Minimal Assumptions on Target Distributions
Ziyu Chen, Hyemin Gu, Markos A. Katsoulakis +2
This paper demonstrates the robustness of Lipschitz-regularized -divergences as objective functionals in generative modeling, showing they enable stable learning across a wide…
Nonlinear denoising score matching for enhanced learning of structured distributions
Jeremiah Birrell, Markos A. Katsoulakis, Luc Rey-Bellet +2
We present a novel method for training score-based generative models which uses nonlinear noising dynamics to improve learning of structured distributions. Generalizing to a nonlin…