Towards Healing the Blindness of Score Matching

Understand

Score-based divergences have been widely used in machine learning and statistics applications.

• Despite their empirical success, a blindness problem has been observed when using these for multi-modal distributions.
• In this work, we discuss the blindness problem and propose a new family of divergences that can mitigate the blindness problem.
• We illustrate our proposed divergence in the context of density estimation and report improved performance compared to traditional approaches.