.png){kind=icon}
.png){kind=icon}
Return
Efficient algorithms for quantum information bottleneck
.png){kind=icon}
OA
AI
DOI：10.22331/q-2023-03-02-936.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
The ability to extract relevant information is critical to learning. An ingenious approach as such is the information bottleneck, an optimi-sation problem whose solution corresponds to a faithful and memory-efficient representation of relevant information from a large system. The advent of the age of quantum computing calls for efficient methods that work on infor-mation regarding quantum systems. Here we address this by proposing a new and general algorithm for the quantum generalisation of in-formation bottleneck. Our algorithm excels in the speed and the definiteness of convergence compared with prior results. It also works for a much broader range of problems, including the quantum extension of deterministic infor-mation bottleneck, an important variant of the original information bottleneck problem. No-tably, we discover that a quantum system can achieve strictly better performance than a clas-sical system of the same size regarding quan-tum information bottleneck, providing new vi-sion on justifying the advantage of quantum machine learning.
Keywords:
CAPACITY