TY - GEN
T1 - ActUp
T2 - 32nd International Joint Conference on Artificial Intelligence, IJCAI 2023
AU - Draganov, Andrew
AU - Jørgensen, Jakob
AU - Scheel, Katrine
AU - Mottin, Davide
AU - Assent, Ira
AU - Berry, Tyrus
AU - Aslay, Cigdem
N1 - Publisher Copyright:
© 2023 International Joint Conferences on Artificial Intelligence. All rights reserved.
PY - 2023/8
Y1 - 2023/8
N2 - tSNE and UMAP are popular dimensionality reduction algorithms due to their speed and interpretable low-dimensional embeddings. Despite their popularity, however, little work has been done to study their full span of differences. We theoretically and experimentally evaluate the space of parameters in both tSNE and UMAP and observe that a single one - the normalization - is responsible for switching between them. This, in turn, implies that a majority of the algorithmic differences can be toggled without affecting the embeddings. We discuss the implications this has on several theoretic claims behind UMAP, as well as how to reconcile them with existing tSNE interpretations. Based on our analysis, we provide a method (GDR) that combines previously incompatible techniques from tSNE and UMAP and can replicate the results of either algorithm. This allows our method to incorporate further improvements, such as an acceleration that obtains either method's outputs faster than UMAP. We release improved versions of tSNE, UMAP, and GDR that are fully plug-and-play with the traditional libraries.
AB - tSNE and UMAP are popular dimensionality reduction algorithms due to their speed and interpretable low-dimensional embeddings. Despite their popularity, however, little work has been done to study their full span of differences. We theoretically and experimentally evaluate the space of parameters in both tSNE and UMAP and observe that a single one - the normalization - is responsible for switching between them. This, in turn, implies that a majority of the algorithmic differences can be toggled without affecting the embeddings. We discuss the implications this has on several theoretic claims behind UMAP, as well as how to reconcile them with existing tSNE interpretations. Based on our analysis, we provide a method (GDR) that combines previously incompatible techniques from tSNE and UMAP and can replicate the results of either algorithm. This allows our method to incorporate further improvements, such as an acceleration that obtains either method's outputs faster than UMAP. We release improved versions of tSNE, UMAP, and GDR that are fully plug-and-play with the traditional libraries.
UR - http://www.scopus.com/inward/record.url?scp=85170378935&partnerID=8YFLogxK
M3 - Article in proceedings
AN - SCOPUS:85170378935
T3 - Proceedings of the International Joint Conference on Artificial Intelligence
SP - 3651
EP - 3658
BT - Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence (IJCAI-23)
PB - International Joint Conferences on Artificial Intelligence
Y2 - 19 August 2023 through 25 August 2023
ER -