QUBO formulation on quantum annealers for joint client selection in federated learning, combined with a MultiSignal routing ensemble, yields higher Byzantine attack detection accuracy than MultiKrum on challenging attacks at both small and moderate scales.
Ising formulations of many NP problems
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
years
2026 4verdicts
UNVERDICTED 4roles
background 2polarities
background 2representative citing papers
Tunneling-augmented simulated annealing optimizes short-block LDPC parity-check matrices to achieve average 0.45 dB SNR gains over random constructions.
A constructive QUBO encoding of small MLWE instances jointly recovers secret and error, with a convex-polytope stability analysis and scaling estimates for quantum annealing.
The paper reviews and extends energy-based dynamical models that use gradient flows and energy landscapes for neurocomputation, learning, and optimization tasks.
citing papers explorer
-
Byzantine-Resilient Federated Learning via QUBO-Based Client Selection on Quantum Annealers
QUBO formulation on quantum annealers for joint client selection in federated learning, combined with a MultiSignal routing ensemble, yields higher Byzantine attack detection accuracy than MultiKrum on challenging attacks at both small and moderate scales.
-
Tunneling-Augmented Simulated Annealing for Short-Block LDPC Code Construction
Tunneling-augmented simulated annealing optimizes short-block LDPC parity-check matrices to achieve average 0.45 dB SNR gains over random constructions.
-
QUBO Modeling of Module Learning With Errors: Stability and Scaling in Post-Quantum Cryptography
A constructive QUBO encoding of small MLWE instances jointly recovers secret and error, with a convex-polytope stability analysis and scaling estimates for quantum annealing.
-
Energy-Based Dynamical Models for Neurocomputation, Learning, and Optimization
The paper reviews and extends energy-based dynamical models that use gradient flows and energy landscapes for neurocomputation, learning, and optimization tasks.