data augmentation 1graph regularization 1learning theory 1self-supervised learning 1semi-supervised learning 1
From the 2 of 2 linked papers with an AI index.
2 papers
cs.LG2026
Avoiding unsafe sets when training with Langevin Dynamics
Adam M. Oberman
Training a model with noisy gradient descent can be idealized as overdamped Langevin dynamics, and a natural safety question is to bound the probability $ν_t(\mathcal{A}_H) = \mat…
cs.LG2026
Fast Rates for Semi-Supervised Learning via Data-Augmentation Graph Regularization
Adam M. Oberman
The paper provides a theoretical analysis showing that self‑supervised learning with data augmentation can achieve a fast O(1/n_L) error rate in semi‑supervised settings, linking t…