Concentration-Free Quantum Kernel Learning in the Rydberg Blockade
read the original abstract
Quantum kernel methods (QKMs) offer an appealing framework for machine learning on near-term quantum computers. However, QKMs generically suffer from exponential concentration, requiring an exponential number of measurements to resolve kernel values, with the exception of trivial (i.e., classically simulable) kernels. Here we propose a QKM that is free of exponential concentration, yet remains hard to simulate classically. Our QKM utilizes the weak ergodicity-breaking many-body dynamics in the Rydberg blockade of coherently driven neutral atom arrays. We demonstrate the fundamental properties of our QKM by analytically solving an approximate toy model of its underpinning quantum dynamics, as well as by extensive numerical simulations on randomly generated datasets. We further show that the proposed kernel exhibits effective learning on real data. The proposed QKM can be implemented in current neutral atom quantum computers. Along the way, we uncover novel physical insights into the thermalization of weak ergodicity-breaking systems through the non-stabilizerness of the underlying Rydberg-blockaded dynamics, which directly governs the classical simulability of the proposed kernel.
This paper has not been read by Pith yet.
Forward citations
Cited by 4 Pith papers
-
Engineering Quantum Many-Body Scars through Lattice Geometry
Transforming the lattice to a triangle-decorated geometry restructures the PXP model's constrained Hilbert space into hypercube subgraphs that stabilize scarring and an approximate su(2) algebra for the fully polarized state.
-
Noise-enhanced quantum kernels on analog quantum computers
Analog quantum kernels with operational noise outperform noiseless versions in benchmarking and non-Markovianity estimation due to increased expressivity and model complexity.
-
Optimal quantum reservoir learning in proximity to universality
A tunable mixing parameter p in random quantum circuits controls the transition from classically simulable to expressive quantum reservoir dynamics via entanglement and nonstabilizer content.
-
Benchmarking a machine-learning differential equations solver on a neutral-atom logical processor
Logical quantum kernels outperform physical ones when solving differential equations on a neutral-atom processor, with gains traced to noise error detection in the logical encoding.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.