all AI news
Enriching Disentanglement: From Logical Definitions to Quantitative Metrics
May 22, 2024, 4:43 a.m. | Yivan Zhang, Masashi Sugiyama
cs.LG updates on arXiv.org arxiv.org
Abstract: Disentangling the explanatory factors in complex data is a promising approach for generalizable and data-efficient representation learning. While a variety of quantitative metrics for learning and evaluating disentangled representations have been proposed, it remains unclear what properties these metrics truly quantify. In this work, we establish a theoretical connection between logical definitions of disentanglement and quantitative metrics using topos theory and enriched category theory. We introduce a systematic approach for converting a first-order predicate into …
abstract arxiv cs.lg data definitions metrics quantitative replace representation representation learning type while work
More from arxiv.org / cs.LG updates on arXiv.org
Machine-learned models for magnetic materials
1 day, 13 hours ago |
arxiv.org
Revisiting RIP guarantees for sketching operators on mixture models
1 day, 13 hours ago |
arxiv.org
Jobs in AI, ML, Big Data
Senior Data Engineer
@ Displate | Warsaw
Senior Machine Learning Engineer
@ GPTZero | Toronto, Canada
BI Developer / Analyst
@ Stoneridge | Novi
BI Developer
@ RIVA Solutions, Inc. | Washington, District Of Columbia, United States
Geography Data Analyst
@ IQVIA | North Sydney, New South Wales, Australia
Demand Planning (Data Analyst) Graduate - Starts in september
@ Puig | Barcelona, B, ES, 08902