arXiv Statistics ML October 27, 2026 By Yuhao Qi, Wenlin Dai, Xuehu Zhu

Synthetic Data Augmentation for Functional Data: Wasserstein Risk Bounds and Diffusion-Based Conditional Generation

Read the original on arXiv Statistics ML →

The Flow has not summarised this story yet — read it at arXiv Statistics ML.

diffusion

arXiv Machine Learning

Oct 21

When Does Training on Synthetic Data Provably Work?

arXiv:2610.28036v1 Announce Type: new Abstract: High-quality training data are a major bottleneck in machine learning, motivating increasing use of artificially generated data. We study when a binary...

By Leroy Odunlami, Tobias Riedlinger, Hanno Gottschalk

benchmarks safety

arXiv Machine Learning

Oct 15

Neural Wasserstein Splines: Representation-Invariant Second-Order Priors for Trajectory Inference

arXiv:2610.19878v1 Announce Type: new Abstract: Population dynamics are often observed only as unpaired snapshots, which leave the evolution between measurements underdetermined. Second-order regular...

By Amartya Banerjee, Harlin Lee, Caroline Moosm\"uller

benchmarks

arXiv Machine Learning

Jun 29

Deep Residual Networks Learn the Geodesic Curve in the Wasserstein Space

arXiv:2102. 09235v3 Announce Type: replace Abstract: Recent studies revealed the mathematical connection between deep neural networks (DNNs) and dynamic systems.

By Kuo Gai, Shihua Zhang

arXiv Machine Learning

Sep 2

On the Reliability of Generative Augmentation: A Wasserstein-Based Theoretical and Empirical Study

arXiv:2609.01410v1 Announce Type: cross Abstract: Generative data augmentation is widely used to mitigate class imbalance, yet its theoretical effect on downstream generalization remains poorly under...

By Chathurika S Abeykoon, Mathias Nthiani Muia, Mallory Goldstein

diffusion data-engineering

arXiv Machine Learning

Jun 25

When Does Synthetic Data Augmentation Improve Score-Based Imbalanced Classification?

arXiv:2606. 26053v1 Announce Type: cross Abstract: Synthetic data augmentation is widely used to mitigate class imbalance, but its theoretical effects on score-based classification remain poorly understood.

By Zhengchi Ma, Pengfei Lyu, Anru R. Zhang

safety

arXiv Machine Learning

Aug 14

Wasserstein Filtering: A Sample Selection Method for Robust Distribution Learning

arXiv:2608. 13418v1 Announce Type: cross Abstract: Given a dataset where a portion of the samples are contaminated, our goal is to recover the underlying clean population distribution.

By Yikai Xu, Zhao Chen, Jian Huang

diffusion benchmarks

One email a morning, machine-written

Related stories

When Does Training on Synthetic Data Provably Work?

Neural Wasserstein Splines: Representation-Invariant Second-Order Priors for Trajectory Inference

Deep Residual Networks Learn the Geodesic Curve in the Wasserstein Space

On the Reliability of Generative Augmentation: A Wasserstein-Based Theoretical and Empirical Study

When Does Synthetic Data Augmentation Improve Score-Based Imbalanced Classification?

Wasserstein Filtering: A Sample Selection Method for Robust Distribution Learning