On the Quantum versus Classical Learnability of Discrete Distributions
Here we study the comparative power of classical and quantum learners for generative modelling within the Probably Approximately Correct (PAC) framework. More specifically we consider the following task: Given samples from some unknown discrete probability distribution, output with high probability...
Main Authors: | Ryan Sweke, Jean-Pierre Seifert, Dominik Hangleiter, Jens Eisert |
---|---|
Format: | Article |
Language: | English |
Published: |
Verein zur Förderung des Open Access Publizierens in den Quantenwissenschaften
2021-03-01
|
Series: | Quantum |
Online Access: | https://quantum-journal.org/papers/q-2021-03-23-417/pdf/ |
Similar Items
-
Stochastic gradient descent for hybrid quantum-classical optimization
by: Ryan Sweke, et al.
Published: (2020-08-01) -
Anticoncentration theorems for schemes showing a quantum speedup
by: Dominik Hangleiter, et al.
Published: (2018-05-01) -
Architectures for Quantum Simulation Showing a Quantum Speedup
by: Juan Bermejo-Vega, et al.
Published: (2018-04-01) -
Deep Learnability: Using Neural Networks to Quantify Language Similarity and Learnability
by: Clara Cohen, et al.
Published: (2020-06-01) -
Learnability for the Information Bottleneck
by: Tailin Wu, et al.
Published: (2019-09-01)