Skip to yearly menu bar Skip to main content


Poster
in
Workshop: NeurIPS 2022 Workshop on Score-Based Methods

Towards Healing the Blindness of Score Matching

Mingtian Zhang · Oscar Key · Peter Hayes · David Barber · Brooks Paige · Francois-Xavier Briol


Abstract:

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.

Chat is not available.