Symmetrizing Bregman divergences on positive definite matrices yields the arithmetic mean as canonical for forward symmetrization and the pulled-back dual arithmetic mean for reverse symmetrization, for any mirror map.
Title resolution pending
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 3verdicts
UNVERDICTED 3roles
background 1polarities
background 1representative citing papers
An integrated neural compression and Cholesky quantum encoding method achieves robust reconstruction and classification performance in noisy quantum channels while bypassing full density matrix reconstruction.
A single functional parameter unifies the entanglement statistics evolution for eigenstates of Hamiltonians represented by multiparametric Gaussian ensembles.
citing papers explorer
-
Symmetrizing Bregman Divergence on the Cone of Positive Definite Matrices: Which Mean to Use and Why
Symmetrizing Bregman divergences on positive definite matrices yields the arithmetic mean as canonical for forward symmetrization and the pulled-back dual arithmetic mean for reverse symmetrization, for any mirror map.
-
End-to-End Neural and Quantum Transcoding for Compressed Latent Representation under Channel Noise
An integrated neural compression and Cholesky quantum encoding method achieves robust reconstruction and classification performance in noisy quantum channels while bypassing full density matrix reconstruction.
-
Entanglement dynamics of many-body quantum states: sensitivity to system conditions and a hidden universality
A single functional parameter unifies the entanglement statistics evolution for eigenstates of Hamiltonians represented by multiparametric Gaussian ensembles.