Binary Classification with Classical Instances and Quantum Labels

In classical statistical learning theory, one of the most well studied problems is that of binary classification. The information-theoretic sample complexity of this task is tightly characterized by the Vapnik-Chervonenkis (VC) dimension. A quantum analog of this task, with training data given as a quantum state has also been intensely studied and is now known to have the same sample complexity as its classical counterpart. We propose a novel quantum version of the classical binary classification task by considering maps with classical input and quantum output and corresponding classical-quantum training data. We discuss learning strategies for the agnostic and for the realizable case and study their performance to obtain sample complexity upper bounds. Moreover, we provide sample complexity lower bounds which show that our upper bounds are essentially tight for pure output states. In particular, we see that the sample complexity is the same as in the classical binary classification task w.r.t. its dependence on accuracy, confidence and the VC-dimension.

[1]  Mark Hoogendoorn,et al.  Mathematical Foundations for Supervised Learning , 2018 .

[2]  Ronald de Wolf,et al.  Optimal Quantum Sample Complexity of Learning Algorithms , 2016, CCC.

[3]  Rocco A. Servedio,et al.  Quantum Algorithms for Learning and Testing Juntas , 2007, Quantum Inf. Process..

[4]  Javed A. Aslam,et al.  On the Sample Complexity of Noise-Tolerant Learning , 1996, Inf. Process. Lett..

[5]  Simone Severini,et al.  mu - biased quantum Fourier sampling , 2018, Quantum Inf. Comput..

[6]  R. Schumann Quantum Information Theory , 2000, quant-ph/0010060.

[7]  Steve Hanneke,et al.  The Optimal Sample Complexity of PAC Learning , 2015, J. Mach. Learn. Res..

[8]  A. Holevo Statistical decision theory for quantum systems , 1973 .

[9]  Anirban Narayan Chowdhury,et al.  A Variational Quantum Algorithm for Preparing Quantum Gibbs States , 2020, 2002.00055.

[10]  Vladimir Vapnik,et al.  Chervonenkis: On the uniform convergence of relative frequencies of events to their probabilities , 1971 .

[11]  Scott Aaronson,et al.  Shadow tomography of quantum states , 2017, Electron. Colloquium Comput. Complex..

[12]  Kai-Min Chung,et al.  Sample Efficient Algorithms for Learning Quantum Channels in PAC Model and the Approximate State Discrimination Problem , 2018, TQC.

[13]  Andrew W. Cross,et al.  Demonstration of quantum advantage in machine learning , 2015, npj Quantum Information.

[14]  T. Heinosaari,et al.  The Mathematical Language of Quantum Theory: From Uncertainty to Entanglement , 2012 .

[15]  Shai Ben-David,et al.  Understanding Machine Learning: From Theory to Algorithms , 2014 .

[16]  Nader H. Bshouty,et al.  Learning DNF over the uniform distribution using a quantum example oracle , 1995, COLT '95.

[17]  Scott Aaronson,et al.  The learnability of quantum states , 2006, Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences.

[18]  Ronald de Wolf,et al.  Two new results about quantum exact learning , 2021, Quantum.

[19]  Ashwin Nayak,et al.  Online learning of quantum states , 2018, NeurIPS.

[20]  D. Angluin,et al.  Learning From Noisy Examples , 1988, Machine Learning.

[21]  Iordanis Kerenidis,et al.  Learning with Errors is easy with quantum samples , 2017, Physical Review A.

[22]  Umesh V. Vazirani,et al.  Quantum complexity theory , 1993, STOC.

[23]  John Watrous,et al.  The Theory of Quantum Information , 2018 .

[24]  Robert S. Kennedy,et al.  Optimum testing of multiple hypotheses in quantum detection theory , 1975, IEEE Trans. Inf. Theory.

[25]  Nagarajan Natarajan,et al.  Learning with Noisy Labels , 2013, NIPS.

[26]  Ashley Montanaro,et al.  The quantum query complexity of learning multilinear polynomials , 2011, Inf. Process. Lett..

[27]  Rocco A. Servedio,et al.  Equivalences and Separations Between Quantum and Classical Learnability , 2004, SIAM J. Comput..

[28]  Srinivasan Arunachalam,et al.  Quantum statistical query learning , 2020, ArXiv.

[29]  Sang Joon Kim,et al.  A Mathematical Theory of Communication , 2006 .

[30]  Srinivasan Arunachalam,et al.  Quantum hardness of learning shallow classical circuits , 2019, Electron. Colloquium Comput. Complex..

[31]  Ping-Cheng Yeh,et al.  The learnability of unknown quantum measurements , 2015, Quantum Inf. Comput..

[32]  Roman Vershynin,et al.  High-Dimensional Probability , 2018 .

[33]  Ronald de Wolf,et al.  Guest Column: A Survey of Quantum Learning Theory , 2017, SIGA.

[34]  Peter L. Bartlett,et al.  Rademacher and Gaussian Complexities: Risk Bounds and Structural Results , 2003, J. Mach. Learn. Res..

[35]  Leslie G. Valiant,et al.  A theory of the learnable , 1984, STOC '84.

[36]  P. Laird Learning from Good and Bad Data , 1988 .