2 papers
cs.IT2025
Information Theoretic Learning for Diffusion Models with Warm Start
Yirong Shen, Lu Gan, Cong Ling
Generative models that maximize model likelihood have gained traction in many practical settings. Among them, perturbation based approaches underpin many strong likelihood estimati…
cs.IT2025
Generalized Score Matching: Bridging -Divergence and Statistical Estimation Under Correlated Noise
Yirong Shen, Lu Gan, Cong Ling
Relative Fisher information, also known as score matching, is a recently introduced learning method for parameter estimation. Fundamental relations between relative entropy and sco…