LHSD uses spectral filtering on the log-density Hessian to isolate tangent directions from noise and estimate local intrinsic dimension scalably via Stochastic Lanczos Quadrature.
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
MIND uses sliced Wasserstein distance on Inception features to evaluate generative models, matching FID performance with 10x fewer samples and 100x faster computation while being more robust to moment-matching attacks.
citing papers explorer
-
Local Hessian Spectral Filtering for Robust Intrinsic Dimension Estimation
LHSD uses spectral filtering on the log-density Hessian to isolate tangent directions from noise and estimate local intrinsic dimension scalably via Stochastic Lanczos Quadrature.
-
MIND: Monge Inception Distance for Generative Models Evaluation
MIND uses sliced Wasserstein distance on Inception features to evaluate generative models, matching FID performance with 10x fewer samples and 100x faster computation while being more robust to moment-matching attacks.