Sobolev regularization on the witness function enables global convergence of MMD gradient flows for both sampling and generative modeling without isoperimetric assumptions.
International Conference on Machine Learning , pages=
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
Trimming helps conformal prediction under contamination precisely when the anomaly score separates retention probabilities without biasing clean scores, otherwise the retained mixture coefficient prevents substantial decontamination.
Geometric tempering yields exponential convergence bounds for both Wasserstein and Fisher-Rao flows but produces no speedup in the Fisher-Rao metric, with new adaptive schedules derived from the tempered dynamics.
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.
-
When Does Trimming Help Conformal Prediction? A Retained-Law Diagnostic under Calibration Contamination
Trimming helps conformal prediction under contamination precisely when the anomaly score separates retention probabilities without biasing clean scores, otherwise the retained mixture coefficient prevents substantial decontamination.
-
Properties and limitations of geometric tempering for gradient flow dynamics
Geometric tempering yields exponential convergence bounds for both Wasserstein and Fisher-Rao flows but produces no speedup in the Fisher-Rao metric, with new adaptive schedules derived from the tempered dynamics.