Practical Equivariances via Relational Conditional Neural Processes

Daolang Huang, Manuel Haussmann, Ulpu Remes, ST John, Grégoire Christophe Clarté, Samuel Kaski, Kevin Luck, Luigi Acerbi

Tutkimustuotos: Artikkeli kirjassa/raportissa/konferenssijulkaisussaKonferenssiartikkeliTieteellinenvertaisarvioitu

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 in spatio-temporal modeling, Bayesian Optimization and continuous control, inherently 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
OtsikkoAdvances in Neural Information Processing Systems 36 (NeurIPS 2023)
ToimittajatA. Oh, T. Neumann, A. Globerson, K. Saenko, M. Hardt, S. Levine
KustantajaMorgan Kaufmann Publishers
Julkaisupäiväjouluk. 2023
DOI - pysyväislinkit
TilaJulkaistu - jouluk. 2023
OKM-julkaisutyyppiA4 Artikkeli konferenssijulkaisuussa
TapahtumaConference on Neural Information Processing Systems 2023 - New Orleans, Yhdysvallat (USA)
Kesto: 10 jouluk. 202316 jouluk. 2023
https://neurips.cc/

Julkaisusarja

NimiAdvances in Neural Information Processing Systems
Vuosikerta36
ISSN (elektroninen)1049-5258

Tieteenalat

  • 113 Tietojenkäsittely- ja informaatiotieteet

Siteeraa tätä