English

Robust Classification with Adiabatic Quantum Optimization

Quantum Physics 2012-05-31 v2

Abstract

We propose a non-convex training objective for robust binary classification of data sets in which label noise is present. The design is guided by the intention of solving the resulting problem by adiabatic quantum optimization. Two requirements are imposed by the engineering constraints of existing quantum hardware: training problems are formulated as quadratic unconstrained binary optimization; and model parameters are represented as binary expansions of low bit-depth. In the present work we validate this approach by using a heuristic classical solver as a stand-in for quantum hardware. Testing on several popular data sets and comparing with a number of existing losses we find substantial advantages in robustness as measured by test error under increasing label noise. Robustness is enabled by the non-convexity of our hardware-compatible loss function, which we name q-loss.

Keywords

Cite

@article{arxiv.1205.1148,
  title  = {Robust Classification with Adiabatic Quantum Optimization},
  author = {Vasil S. Denchev and Nan Ding and S. V. N. Vishwanathan and Hartmut Neven},
  journal= {arXiv preprint arXiv:1205.1148},
  year   = {2012}
}

Comments

17 pages, 5 figures, accepted by ICML 2012

R2 v1 2026-06-21T20:59:05.564Z