Sobolev regularization on the witness function enables global convergence of MMD gradient flows for both sampling and generative modeling without isoperimetric assumptions.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
WARDEN is a new adversarial training framework for large language models that minimizes worst-case loss over an f-divergence ambiguity set, reducing attack success rates while keeping utility comparable to recent baselines.
citing papers explorer
-
Sobolev Regularized MMD Gradient Flow
Sobolev regularization on the witness function enables global convergence of MMD gradient flows for both sampling and generative modeling without isoperimetric assumptions.
-
Information Theoretic Adversarial Training of Large Language Models
WARDEN is a new adversarial training framework for large language models that minimizes worst-case loss over an f-divergence ambiguity set, reducing attack success rates while keeping utility comparable to recent baselines.