QuAnt: Quantum Annealing with Learnt Couplings
This addresses the problem for researchers and practitioners in quantum computing and computer vision by enabling flexible and compact solution encodings, though it is incremental as it builds on existing quantum annealing methods.
The paper tackles the challenge of deriving suitable QUBO forms for combinatorial optimization in computer vision by proposing to learn them from data via gradient backpropagation, resulting in competitive performance with the quantum state of the art while requiring fewer qubits and scaling to larger problems.
Modern quantum annealers can find high-quality solutions to combinatorial optimisation objectives given as quadratic unconstrained binary optimisation (QUBO) problems. Unfortunately, obtaining suitable QUBO forms in computer vision remains challenging and currently requires problem-specific analytical derivations. Moreover, such explicit formulations impose tangible constraints on solution encodings. In stark contrast to prior work, this paper proposes to learn QUBO forms from data through gradient backpropagation instead of deriving them. As a result, the solution encodings can be chosen flexibly and compactly. Furthermore, our methodology is general and virtually independent of the specifics of the target problem type. We demonstrate the advantages of learnt QUBOs on the diverse problem types of graph matching, 2D point cloud alignment and 3D rotation estimation. Our results are competitive with the previous quantum state of the art while requiring much fewer logical and physical qubits, enabling our method to scale to larger problems. The code and the new dataset will be open-sourced.