On learning finite-state quantum sources

We examine the complexity of learning the distributions produced by finite-state quantum sources. We show how prior techniques for learning hidden Markov models can be adapted to the quantum generator model to find that the analogous state of affairs holds: information-theoretically, a polynomial number of samples suffice to approximately identify the distribution, but computationally, the problem is as hard as learning parities with noise, a notorious open question in computational learning theory.

[1]  Elchanan Mossel,et al.  Learning nonsingular phylogenies and hidden Markov models , 2005, STOC '05.

[2]  James P. Crutchfield,et al.  Computation in Finitary Stochastic and Quantum Processes , 2006 .

[3]  Ronitt Rubinfeld,et al.  On the learnability of discrete distributions , 1994, STOC '94.

[4]  Dana Angluin,et al.  Learning from noisy examples , 1988, Machine Learning.

[5]  A. Winter,et al.  Randomizing Quantum States: Constructions and Applications , 2003, quant-ph/0307104.

[6]  Sham M. Kakade,et al.  A spectral algorithm for learning Hidden Markov Models , 2008, J. Comput. Syst. Sci..

[7]  Naoki Abe,et al.  On the computational complexity of approximating distributions by probabilistic automata , 1990, Machine Learning.

[8]  D. Pollard.  Convergence of stochastic processes , 1984 .

[9]  Stanley Gudder,et al.  Quantum Automata: An Overview , 1999 .

[10]  A. Kitaev.  Quantum computations: algorithms and error correction , 1997 .

[11]  Rusins Freivalds,et al.  Quantum Finite State Transducers , 2001, SOFSEM.

[12]  Vitaly Feldman,et al.  On Agnostic Learning of Parities, Monomials, and Halfspaces , 2009, SIAM J. Comput..

[13]  R. Schapire,et al.  Toward Efficient Agnostic Learning , 1994 .

[14]  Vitaly Feldman,et al.  New Results for Learning Noisy Parities and Halfspaces , 2006, 2006 47th Annual IEEE Symposium on Foundations of Computer Science (FOCS'06).

[15]  Andris Ambainis,et al.  1-way quantum finite automata: strengths, weaknesses and generalizations , 1998, Proceedings 39th Annual Symposium on Foundations of Computer Science (Cat. No.98CB36280).

[16]  Andris Ambainis,et al.  Improved constructions of quantum automata , 2009, Theor. Comput. Sci..

[17]  Michael Kearns,et al.  Efficient noise-tolerant learning from statistical queries , 1993, STOC.

[18]  Yishay Mansour,et al.  Weakly learning DNF and characterizing statistical query learning using Fourier analysis , 1994, STOC '94.

[19]  Richard J. Lipton,et al.  Cryptographic Primitives Based on Hard Learning Problems , 1993, CRYPTO.