Quantum RΓ©nyi and $f$-divergences from integral representations
June 21, 2023 Β· Declared Dead Β· π Communications in Mathematical Physics
"No code URL or promise found in abstract"
Evidence collected by the PWNC Scanner
Authors
Christoph Hirche, Marco Tomamichel
arXiv ID
2306.12343
Category
quant-ph: Quantum Computing
Cross-listed
cs.IT
Citations
33
Venue
Communications in Mathematical Physics
Last Checked
6 months ago
Abstract
Smooth CsiszΓ‘r $f$-divergences can be expressed as integrals over so-called hockey stick divergences. This motivates a natural quantum generalization in terms of quantum Hockey stick divergences, which we explore here. Using this recipe, the Kullback-Leibler divergence generalises to the Umegaki relative entropy, in the integral form recently found by Frenkel. We find that the RΓ©nyi divergences defined via our new quantum $f$-divergences are not additive in general, but that their regularisations surprisingly yield the Petz RΓ©nyi divergence for $Ξ±< 1$ and the sandwiched RΓ©nyi divergence for $Ξ±> 1$, unifying these two important families of quantum RΓ©nyi divergences. Moreover, we find that the contraction coefficients for the new quantum $f$ divergences collapse for all $f$ that are operator convex, mimicking the classical behaviour and resolving some long-standing conjectures by Lesniewski and Ruskai. We derive various inequalities, including new reverse Pinsker inequalities with applications in differential privacy and explore various other applications of the new divergences.
Community Contributions
Found the code? Know the venue? Think something is wrong? Let us know!
π Similar Papers
In the same crypt β Quantum Computing
R.I.P.
π»
Ghosted
R.I.P.
π»
Ghosted
Quantum machine learning: a classical perspective
R.I.P.
π»
Ghosted
Noise-Adaptive Compiler Mappings for Noisy Intermediate-Scale Quantum Computers
R.I.P.
π»
Ghosted
ProjectQ: An Open Source Software Framework for Quantum Computing
R.I.P.
π»
Ghosted
Quantum Recommendation Systems
R.I.P.
π»
Ghosted
Traffic flow optimization using a quantum annealer
Died the same way β π» Ghosted
R.I.P.
π»
Ghosted
Federated Learning: Strategies for Improving Communication Efficiency
R.I.P.
π»
Ghosted
In-Datacenter Performance Analysis of a Tensor Processing Unit
R.I.P.
π»
Ghosted
Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning
R.I.P.
π»
Ghosted