Cargando…
Efficiency of quantum vs. classical annealing in nonconvex learning problems
Quantum annealers aim at solving nonconvex optimization problems by exploiting cooperative tunneling effects to escape local minima. The underlying idea consists of designing a classical energy function whose ground states are the sought optimal solutions of the original optimization problem and add...
Autores principales: | Baldassi, Carlo, Zecchina, Riccardo |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
National Academy of Sciences
2018
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5816144/ https://www.ncbi.nlm.nih.gov/pubmed/29382764 http://dx.doi.org/10.1073/pnas.1711456115 |
Ejemplares similares
-
Efficient supervised learning in networks with binary synapses
por: Baldassi, Carlo, et al.
Publicado: (2007) -
Nonconvex optimal control and variational problems
por: Zaslavski, Alexander J
Publicado: (2013) -
Shaping the learning landscape in neural networks around wide flat minima
por: Baldassi, Carlo, et al.
Publicado: (2020) -
A Three-Threshold Learning Rule Approaches the Maximal Capacity of Recurrent Neural Networks
por: Alemi, Alireza, et al.
Publicado: (2015) -
From convexity to nonconvexity
por: Gilbert, R, et al.
Publicado: (2001)