Robust classification with adiabatic quantum optimization

Proceedings of the 29th International Conference on Machine Learning, ICML 2012

Volumn 1, Issue , 2012, Pages 863-870

  Denchev, Vasil S ^a   Ding, Nan ^a   Vishwanathan, S V N ^a   Neven, Hartmut ^b  

^a PURDUE UNIVERSITY   (United States)

^b GOOGLE INC   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

BINARY CLASSIFICATION; BINARY EXPANSIONS; BINARY OPTIMIZATION; BIT DEPTH; DATA SETS; ENGINEERING CONSTRAINTS; LOSS FUNCTIONS; MODEL PARAMETERS; NONCONVEXITY; QUANTUM OPTIMIZATION; ROBUST CLASSIFICATION; TEST ERRORS;

HARDWARE; LEARNING SYSTEMS;

OPTIMIZATION;

EID: 84867123336     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (29)

1. Balay, S., Brown, J., Buschelman, K., Gropp, W. D., Kaushik, D., Knepley, M. G., McInnes, L. C., Smith, B. F., and Zhang, H. PETSc Web page, 2011. http://www.mcs.anl.gov/petsc.
2. Benson, S., McInnes, L. C., Moré, J., Munson, T., and Sarich, J. TAO user manual (revision 1.10.1). Technical Report ANL/MCS-TM-242, Mathematics and Computer Science Division, Argonne National Laboratory, 2010. http://www.mcs.anl.gov/tao.
3. Bishop, C. M. Pattern Recognition and Machine Learning. Springer-Verlag New York, Inc., 2006.
4. Brush, S. History of the Lenz-Ising model. Reviews of Modern Physics, 39:883-893, 1967.
5. Collobert, R., Weston, J., and Bottou, L. Trading convexity for scalability. In Proceedings ICML, 2006.
6. Dempster, A. P., Laird, N. M., and Rubin, D. B. Maximum likelihood from incomplete data via the EM algorithm. Journal of the Royal Statistical Soc. B, 39(1):1-38, 1977.
7. Denchev, V. S., Ding, N., Vishwanathan, S. V. N., and Neven, H. Robust classification with adiabatic quantum optimization. 2012. arXiv:1205.1148v2.
8. Dickson, Neil G. and Amin, Mohammad H. Algorithmic approach to adiabatic quantum optimization, 2011. arXiv:1108.3303v1.
9. Dietterich, Thomas G. Approximate statistical tests for comparing supervised classification learning algorithms. Neural Computation, 10:1895-1923, 1998.
10. Ding, N. and Vishwanathan, S. V. N. t-logistic regression. In Proceedings NIPS, 2010.
11. Ertekin, S., Bottou, L., and Giles, C. L. Ignorance is bliss: Non-convex online support vector machines. IEEE Transactions on Pattern Recognition and Machine Intelligence, 33(2):368-381, 2011.
12. Fan, R. E., Chang, K. W., Hsieh, C. J., Wang, X. R., and Lin, C. J. LIBLINEAR: A library for large linear classification. JMLR, 9:1871-1874, 2008.
13. Farhi, E., Goldstone, J., Gutmann, S., and Sipser, M. Quantum computation by adiabatic evolution. 2000. arXiv:quant-ph/0001106v1.
14. Feldman, V., Guruswami, V., Raghavendra, P., and Wu, Y. Agnostic learning of monomials by halfspaces is hard. 2010. arXiv:1012.0729v1.
15. Freund, Y. A more robust boosting algorithm. Technical report, 2009. arXiv:0905.2138v1.
16. Johnson, M. W., Amin, M. H. S., Gildert, S., Lanting, T., Hamze, F., Dickson, N., Harris, R., Berkley, A. J., Johansson, J., Bunyk, P., Chappie, E. M., Enderud, C., Hilton, J. P., Karimi, K., Ladizinsky, E., Ladizinsky, N., Oh, T., Perminov, I., Rich, C., Thorn, M. C., Tolkacheva, E., Truncik, C. J. S., Uchaikin, S., Wang, J., Wilson, B., and Rose, G. Quantum annealing with manufactured spins. Nature, 473(7346):194-198, May 2011.
17. Jordan, Michael I., Ghahramani, Zoubin, Jaakkola, Tommi S., and Saul, Lawrence K. An introduction to variational methods for graphical models. Machine Learning, 37:183-233, November 1999.
18. Liu, D. C., Nocedal, J., and Dong, C. On the limited memory BFGS method for large scale optimization. Mathematical Programming, 45:503-528, 1989.
19. Long, P. M. and Servedio, R. A. Random classification noise defeats all convex potential boosters. Machine Learning Journal, 783:287-304, 2010.
20. Manwani, N. and Sastry, P. S. Noise tolerance under risk minimization. 2011. arXiv:1109.5231v2.
21. Masnadi-Shirazi, H., Mahadevan, V., and Vasconcelos, N. On the design of robust classifiers for computer vision. In CVPR, pp. 779-786, 2010.
22. Mease, D. and Wyner, A. Evidence contrary to the statistical view of boosting. JMLR, 9:131-156, 2007.
23. Neven, H., Denchev, V. S., Rose, G., and MacReady, W. G. Training a binary classifier with the quantum adiabatic algorithm. 2008. arXiv:0811.0416v1.
24. Neven, H., Denchev, V. S., Drew-Brook, M., Zhang, J., Macready, W. G., and Rose, G. NIPS 2009 demonstration: Binary classification using hardware implementation of quantum annealing. December 2009a.
25. Neven, H., Denchev, V. S., Rose, G., and MacReady, W. G. Training a large scale classifier with the quantum adiabatic algorithm. 2009b. arXiv:0912.0779v1.
26. Palubeckis, G. Multistart tabu search strategies for the unconstrained binary quadratic optimization problem. Ann. Oper. Res., 131:259-282, 2004.
27. Vapnik, V. Statistical learning theory. Wiley, 1998.
28. Yuille, A. L. and Rangarajan, A. The concave-convex procedure (CCCP). In Proceedings NIPS, 2002.
29. Zhang, X., Saha, A., and Vishwanathan, S. V. N. Regularized risk minimization by Nesterov's accelerated gradient methods: Algorithmic extensions and empirical studies. 2010. arXiv:1011.0472v1.