Feasible value functions in POMDPs under memoryless policies form a semi-algebraic set defined by polynomial inequalities from the model parameters.
The golden-thompson trace inequality is complemented
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
Derives generalization bounds for quantum learning via quantum and classical Rényi divergences, with a new modified sandwich quantum Rényi divergence shown to outperform the Petz version analytically and numerically.
Rényi entropy is subadditive on the majorization lattice for every α ∈ [0,∞] and supermodular for α ∈ {0} ∪ [1,∞]; Tsallis entropy is subadditive and supermodular for all α ∈ [0,∞).
Branch-resolved Choi-shadow benchmarking of teleportation shows the relative benefit of PROM mitigation vs post-processing flips depending on mid-circuit readout error.
In the BNT neutrino mass model the electroweak vacuum is not generically the global minimum, with stability reducible to two mass inequalities when the quadruplet vev vanishes.
Develops a convex optimization method using graph Laplacians and linear matrix inequalities to minimize expected synchronization cost in lossless power networks, validated on the IEEE 30-bus test system with reported reductions in transients.
citing papers explorer
-
The Value Function Semi-Algebraic Set in Partially Observable Markov Decision Processes
Feasible value functions in POMDPs under memoryless policies form a semi-algebraic set defined by polynomial inequalities from the model parameters.
-
Generalization Bounds for Quantum Learning via R\'enyi Divergences
Derives generalization bounds for quantum learning via quantum and classical Rényi divergences, with a new modified sandwich quantum Rényi divergence shown to outperform the Petz version analytically and numerically.
-
Geometry of R\'enyi Entropy on the Majorization Lattice
Rényi entropy is subadditive on the majorization lattice for every α ∈ [0,∞] and supermodular for α ∈ {0} ∪ [1,∞]; Tsallis entropy is subadditive and supermodular for all α ∈ [0,∞).
-
Branch-Resolved Characterization of Feed-Forward Error in Dynamic Teleportation via Classical Choi Shadows
Branch-resolved Choi-shadow benchmarking of teleportation shows the relative benefit of PROM mitigation vs post-processing flips depending on mid-circuit readout error.
-
Vacuum structure of the Babu-Nandi-Tavartkiladze model of neutrino mass generation
In the BNT neutrino mass model the electroweak vacuum is not generically the global minimum, with stability reducible to two mass inequalities when the quadruplet vev vanishes.
-
Minimizing the Expected Cost of Synchronization in Lossless Power Networks
Develops a convex optimization method using graph Laplacians and linear matrix inequalities to minimize expected synchronization cost in lossless power networks, validated on the IEEE 30-bus test system with reported reductions in transients.