RECORD
Training quantum neural networks using the Quantum Information Bottleneck method
Quantum Physics · Submitted 5 Dec 2022
abstract compiled · 2026-09-23 · no language-model review
The authors' main claim We further provide algorithms for estimating the derivatives of the QIB function, showing that quantum neural networks can be trained efficiently using the QIB quantity given that the number of gradient steps required is polynomial.
The compiled record
The paper's own sentences, arranged. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. Numbers in the tables are the authors', checked by code. No sentence in this record was written by a model.
Open the compiled record
The abstract, sentence by sentence
We provide in this paper a concrete method for training a quantum neural network to maximize the relevant information about a property that is transmitted through the network. This is significant because it gives an operationally well founded quantity to optimize when training autoencoders for problems where the inputs and outputs are fully quantum. We provide a rigorous algorithm for computing the value of the quantum information bottleneck quantity within error $\epsilon$ that requires $O(\log^2(1/\epsilon) + 1/\delta^2)$ queries to a purification of the input density operator if its spectrum is supported on $\{0\}~\bigcup ~[\delta,1-\delta]$ for $\delta>0$ and the kernels of the relevant density matrices are disjoint. We further provide algorithms for estimating the derivatives of the QIB function, showing that quantum neural networks can be trained efficiently using the QIB quantity given that the number of gradient steps required is polynomial.
background contribution method result interpretation main claim
| # | sentence | role | the authors' own work | states the main conclusion | strength |
|---|---|---|---|---|---|
| s0 | We provide in this paper a concrete method for training a quantum neural network to maximize the relevant information about a property that is transmitted through the network. | contribution 0.98 | 0.94 | 0.55 | asserted 1.00 |
| s1 | This is significant because it gives an operationally well founded quantity to optimize when training autoencoders for problems where the inputs and outputs are fully quantum. | interpretation 0.99 | 0.38 | 0.18 | asserted 0.99 |
| s2 | We provide a rigorous algorithm for computing the value of the quantum information bottleneck quantity within error $\epsilon$ that requires $O(\log^2(1/\epsilon) + 1/\delta^2)$ queries to a purification of the input density operator if its spectrum is supported on $\{0\}~\bigcup ~[\delta,1-\delta]$ for $\delta>0$ and the kernels of the relevant density matrices are disjoint. | contribution 0.49 | 0.95 | 0.13 | asserted 1.00 |
| s3 | We further provide algorithms for estimating the derivatives of the QIB function, showing that quantum neural networks can be trained efficiently using the QIB quantity given that the number of gradient steps required is polynomial. | contribution 0.83 | 0.93 | 0.28 | asserted 0.91 |
What was examined, and what was not
- arXiv listing abstract v2
- full text
- figures and tables
- references and citing sentences
- relations to other papers
- P abstract
- S sections
- T body sentences
- C citations
- R cross-paper relations
The paper
Original abstract
We provide in this paper a concrete method for training a quantum neural network to maximize the relevant information about a property that is transmitted through the network. This is significant because it gives an operationally well founded quantity to optimize when training autoencoders for problems where the inputs and outputs are fully quantum. We provide a rigorous algorithm for computing the value of the quantum information bottleneck quantity within error $\epsilon$ that requires $O(\log^2(1/\epsilon) + 1/\delta^2)$ queries to a purification of the input density operator if its spectrum is supported on $\{0\}~\bigcup ~[\delta,1-\delta]$ for $\delta>0$ and the kernels of the relevant density matrices are disjoint. We further provide algorithms for estimating the derivatives of the QIB function, showing that quantum neural networks can be trained efficiently using the QIB quantity given that the number of gradient steps required is polynomial.
Human review
How the literature uses it
What this paper does with the arXiv papers it cites
What it cites · 5 sentences without a confident label
Uses the method or tool of 1 paper
-
In this circuit, the probability of measuring $|0⟩$ on the auxiliary qubit is given by [ref] :
Quantum Generative Training Using R\'enyi Divergences · Calculation of traces of polynomials of density operators · 0.90
Discussion
Know something about this paper? Leave a comment, or highlight any passage above to comment on it.