Submodular Mini-Batch Training in Generative Moment Matching Networks
Jun Qi
TL;DR
This paper discusses a novel mini-batch training method for generative moment matching networks based on submodular optimization, aiming to improve training efficiency and model quality.
Contribution
It introduces a submodular mini-batch selection technique specifically designed for generative moment matching networks, enhancing training performance.
Findings
Improved training efficiency demonstrated on benchmark datasets
Enhanced quality of generated samples compared to baseline methods
Scalability of the approach to larger models and datasets
Abstract
This article was withdrawn because (1) it was uploaded without the co-authors' knowledge or consent, and (2) there are allegations of plagiarism.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsTopic Modeling · Music and Audio Processing · Speech and dialogue systems