Abstrakti

Conditional Neural Processes (CNPs) are a class of metalearning models popular for combining the runtime efficiency of amortized inference with reliable uncertainty quantification. Many relevant machine learning tasks, such as spatio-temporal modeling, Bayesian Optimization and continuous control, contain equivariances -- for example to translation -- which the model can exploit for maximal performance. However, prior attempts to include equivariances in CNPs do not scale effectively beyond two input dimensions. In this work, we propose Relational Conditional Neural Processes (RCNPs), an effective approach to incorporate equivariances into any neural process model. Our proposed method extends the applicability and impact of equivariant neural processes to higher dimensions. We empirically demonstrate the competitive performance of RCNPs on a large array of tasks naturally containing equivariances.
AlkuperäiskieliEnglanti
Sivumäärä38
TilaHyväksytty/In press - 24 syysk. 2023
OKM-julkaisutyyppiEi oikeutettu
TapahtumaConference on Neural Information Processing Systems - Ernest N. Morial Convention Center, New Orleans, Yhdysvallat
Kesto: 10 jouluk. 202316 jouluk. 2023
Konferenssinumero: 37
https://nips.cc/

Conference

ConferenceConference on Neural Information Processing Systems
LyhennettäNeurIPS
Maa/AlueYhdysvallat
KaupunkiNew Orleans
Ajanjakso10/12/202316/12/2023
www-osoite

Sormenjälki

Sukella tutkimusaiheisiin 'Practical Equivariances via Relational Conditional Neural Processes'. Ne muodostavat yhdessä ainutlaatuisen sormenjäljen.

Siteeraa tätä