Robust Classification with Adiabatic Quantum Optimization

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.

17 pages, 5 figures, accepted by ICML 2012

References in corpus (6)

• Noise Tolerance under Risk Minimization
• A more robust boosting algorithm
• Training a Binary Classifier with the Quantum Adiabatic Algorithm
• Training a Large Scale Classifier with the Quantum Adiabatic Algorithm
• Algorithmic approach to adiabatic quantum optimization
• Regularized Risk Minimization by Nesterov's Accelerated Gradient Methods: Algorithmic Extensions and Empirical Studies

Cited by in corpus (7)

• Quantum Machine Learning
• Ising formulations of many NP problems
• Adiabatic Quantum Simulation of Quantum Chemistry
• Optimized simulated annealing for Ising spin glasses
• Near-Term Quantum-Classical Associative Adversarial Networks
• Construction of non-convex polynomial loss functions for training a binary classifier with quantum annealing
• Making Convex Loss Functions Robust to Outliers using $e$-Exponentiated Transformation