Learning DNFs under product distributions via μ-biased quantum Fourier sampling
We show that DNF formulae can be quantum PAC-learned in polynomial time under product distributions using a quantum example oracle. The current best classical algorithm runs in superpolynomial time. Our result extends the work by Bshouty and Jackson (1998) that proved that DNF formulae are efficient...
Main Authors: | Kanade, V, Rocchetto, A, Severini, S |
---|---|
Format: | Journal article |
Sprog: | English |
Udgivet: |
Rinton Press
2019
|
Lignende værker
-
Learning hard quantum distributions with variational autoencoders
af: Rocchetto, A, et al.
Udgivet: (2018) -
Modelling non-markovian quantum processes with recurrent neural networks
af: Banchi, L, et al.
Udgivet: (2018) -
Modelling non-markovian quantum processes with recurrent neural networks
af: Leonardo Banchi, et al.
Udgivet: (2018-01-01) -
Experimental learning of quantum states
af: Rocchetto, A, et al.
Udgivet: (2019) -
Algorithmic models in quantum mechanics
af: Rocchetto, A
Udgivet: (2019)