UCL Discovery
UCL home » Library Services » Electronic resources » UCL Discovery

Towards Healing the Blindness of Score Matching

Zhang, Mingtian; Key, Oscar; Hayes, Peter; Barber, David; Paige, Brooks; Briol, François-Xavier; (2022) Towards Healing the Blindness of Score Matching. arXiv: Ithaca (NY), USA. Green open access

[thumbnail of 2209.07396v2.pdf]
Preview
Text
2209.07396v2.pdf - Accepted Version

Download (538kB) | Preview

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.

Type: Working / discussion paper
Title: Towards Healing the Blindness of Score Matching
Open access status: An open access version is available from UCL Discovery
Publisher version: https://doi.org/10.48550/arXiv.2209.07396
Language: English
Additional information: For information on re-use, please refer to the publisher’s terms and conditions.
UCL classification: UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Maths and Physical Sciences
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Maths and Physical Sciences > Dept of Statistical Science
UCL > Provost and Vice Provost Offices > UCL BEAMS
UCL
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science
URI: https://discovery.ucl.ac.uk/id/eprint/10158234
Downloads since deposit
12Downloads
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item