Balancing Expressivity and Learnability in Quantum Kernel Bandit Optimization
We investigate Gaussian process (GP) bandit optimization with quantum kernels, assuming the mean reward function lies in the reproducing kernel Hilbert space (RKHS) induced by the quantum kernel. This setting is motivated by NISQ-era tasks such as quantum control, state preparation and variational quantum algorithms. While quantum kernels can offer a `quantum advantage' via domain-specific inductive biases, naïvely using full, high-dimensional kernels increases model complexity and information gain, leading to higher cumulative regret and poor learnability. To address this, we propose projecte
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- LinkedLinked via unknownFareedKhan-dev/agentic-quantum-computing →
- LinkedLinked via arxiv author · 85%Yuqi Huang →
“Balancing Expressivity and Learnability in Quantum Kernel Bandit Optimization”
- LinkedLinked via arxiv author · 85%Vincent Y. F. Tan →
“Balancing Expressivity and Learnability in Quantum Kernel Bandit Optimization”
- LinkedLinked via arxiv author · 85%Sharu Theresa Jose →
“Balancing Expressivity and Learnability in Quantum Kernel Bandit Optimization”
- PossiblePossibly related (embedding) · 53%netket/netket →
- PossiblePossibly related (embedding) · 48%google-research/hyperbo →
- PossiblePossibly related (embedding) · 50%Towards a quantum computer that learns from its errors - Google Research →
- FuzzySimilar title/name (fuzzy) · 59%microsoft/semantic-kernel →
“Fuzzy title match (0.73): “Balancing Expressivity and Learnability in Quantum Kernel Ba” ≈ “microsoft/semantic-kernel””