Computability of optimizers

DOI10.1109/TIT.2023.3347071MaRDI QIDQ6576273zbMATH OpenFDO

Authors Yunseok Lee, Holger Boche, Gitta Kutyniok

Publication date 22 July 2024

Published in IEEE Transactions on Information Theory (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1109/TIT.2023.3347071

zbMATH Keywords

computabilityinformation theoryneural networksoptimization problemsTuring machinesWasserstein distance

Mathematics Subject Classification ID

Turing machines and related notions (03D10) Classical models of computation (Turing machines, etc.) (68Q04) Artificial neural networks and deep learning (68T07) Sensitivity, stability, parametric optimization (90C31) Programming in abstract spaces (90C48) Portfolio theory (91G10) Information theory (general) (94A15) Cryptography (94A60)

Cited in

(4)

• A decidable class of inferences in first-order objective Bayesian inductive logic
• Computability of classification and deep learning: from theoretical limits to practical feasibility through quantization
• Minimal trellises for non-degenerate and degenerate decoding of quantum stabilizer codes
• On effective convergence in Fekete's lemma and related combinatorial problems in information theory

This page was built for publication: Computability of optimizers

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6576273)