Computing a nonnegative matrix factorization-provably

SIAM Journal on Computing

Volumn 45, Issue 4, 2016, Pages 1582-1611

  Arora, Sanjeev ^a   Ge, Rong ^a   Kannan, Ravi ^b   Moitra, Ankur ^c  

^a Princeton University   (United States)

^b MICROSOFT RESEARCH   (United States)

^c INSTITUTE FOR ADVANCED STUDY   (United States)

Author keywords

Nonnegative matrix factorization; Provable algorithms; Separability

Indexed keywords

ARTIFICIAL INTELLIGENCE; FACTORIZATION; HEURISTIC ALGORITHMS; LEARNING SYSTEMS; POLYNOMIAL APPROXIMATION; POLYNOMIALS; PROBABILITY; PROBLEM SOLVING; QUANTUM THEORY; SINGULAR VALUE DECOMPOSITION;

COMMUNICATION COMPLEXITY; LOCAL SEARCH HEURISTICS; NON-NEGATIVE MATRIX; NONNEGATIVE MATRIX FACTORIZATION; POLYHEDRAL COMBINATORICS; POLYNOMIAL-TIME ALGORITHMS; SEPARABILITY; SUBEXPONENTIAL TIME;

MATRIX ALGEBRA;

EID: 84990975264     PISSN: 00975397     EISSN: 10957111     Source Type: Journal    
DOI: 10.1137/130913869     Document Type: Conference Paper

References (39)

1. A. Aho, J. Ullman, and M. Yannakakis, On notions of information transfer in VLSI circuits, in STOC, ACM, New York, 1983, pp. 133-139.
2. N. Alon and S. Onn, Separable partitions, Discrete Appl. Math., 91 (1999), pp. 39-51.
3. S. Arora, R. Ge, R. Kannan, and A. Moitra, Computing a nonnegative matrix factorization provably, in STOC, ACM, New York, 2012, pp. 145-162.
4. S. Arora, R. Ge, and A. Moitra, Learning topic models -going beyond SVD, in FOCS, IEEE Computer Society, Los Alamites, CA, 2012, pp. 1-10.
5. S. Arora, R. Ge, Y. Halpern, D. Mimno, A. Moitra, D. Sontag, Y. Wu, and M. Zhu, A practical algorithm for topic modeling with provable guarantees, J. Mach. Learn. Res. Workshop Conf. Proc., 28 (2013), pp. 280-288.
6. S. Basu, R. Pollack, and M. Roy, On the combinatorial and algebraic complexity of quantifier elimination, J. ACM, 43 (1996), pp. 1002-1045.
7. V. Bittorf, B. Recht, C. Re, and J. Tropp, Factoring nonnegative matrices with linear programs, in NIPS, Curran, Red Hook, NY, 2012, pp. 1223-1231.
8. D. Blei, private communication, 2011.
9. D. Blei, A. Ng, and M. Jordan, Latent Dirichlet allocation, J. Mach. Learn. Res., 3 (2003), pp. 993-1022.
10. L. Blum, F. Cucker, M. Shub, and S. Smale, Complexity Real Computations, Springer Verlag, New York, 1998.
11. G. Buchsbaum and O. Bloch, Color categories revealed by non-negative matrix factorization of Munsell color spectra, Vis. Res., 42 (2002), pp. 559-563.
12. J. Cohen and U. Rothblum, Nonnegative ranks, decompositions and factorizations of nonnegative matices, Linear Algebra Appl., 190 (1993), pp. 149-168.
13. S. Deerwester, S. Dumais, T. Landauer, G. Furnas, and R. Harshman, Indexing by latent semantic analysis, J. Assoc. Inform. Sci. Technol., 41 (1990), pp. 391-407.
14. D. Donoho and V. Stodden, When does non-negative matrix factorization give the correct decomposition into parts?, in NIPS, Curran, Red Hook, NY, 2003.
15. S. Fiorini, T. Rothvoß, and H. Tiwary, Extended formulations for polygons, Discrete Com-put. Geom., 48 (2012), pp. 658-668.
16. N. Gillis, Robust Analysis of HottTopixx, a Linear Programming Model for Factoring Nonnegative Matrices, preprint, arXiv:1211.6687, 2012.
17. N. Gillis and S. Vavasis, Fast and robust recursive algorithms for separable nonnegative matrix factorization, preprint, arXiv:1208.1237, 2012.
18. G. Golub and C. van Loan, Matrix Computations, The Johns Hopkins University Press, Baltmore, 1996.
19. D. Yu. Grigor'ev and N. N. Vorobjov, Jr., Solving systems of polynomial inequalities in subexponential time, J. Symbolic Comput., 5 (1988), pp. 37-64.
20. E. Harding, The number of partitions of a set of N points in k dimensions induced by hyper-planes, Proc. Edinb. Math. Soc. (2), 15 (1967), pp. 285-289.
21. L. Henry, Schémas de nuptialité: déséquilibre des sexes et célibat, Population, 24 (1969), pp. 457-486.
22. T. Hofmann, Probabilistic latent semantic analysis, in uncertainly in artificial intelligence, Morgan Kautmann, San Francisco, 1999, pp. 289-296.
23. F. Hwang and U. Rothblum, On the number of separable partitions, J. Combin. Optim., 21 (2011), pp. 423-433.
24. R. Impagliazzo and R. Paturi, On the complexity of k-SAT, J. Comput. System Sci., 62 (2001), pp. 367-375.
25. A. Kumar, V. Sindhwani, and P. Kambadur, Fast conical hull algorithms for near-separable non-negative matrix factorization, J. Mac. Learn. Res. Workshop Conf. Proc., 28 (2013), pp. 231-239.
26. W. Lawton and E. Sylvestre, Self modeling curve resolution, Technometrics, 13 (1971), pp. 617-633.
27. D. Lee and H. Seung, Learning the parts of objects by non-negative matrix factorization, Nature, 401 (1999), pp. 788-791.
28. D. Lee and H. Seung, Algorithms for non-negative matrix factorization, in NIPS, MIT Press, Cambridge, MA, 2000, pp. 556-562.
29. L. Lovász and M. Saks. Communication complexity and combinatorial lattice theory, J. Com-put. System Sci., 47 (1993), pp. 322-349.
30. A. Moitra, An almost optimal algorithm for computing nonnegative rank, in SODA, Curran, Red Hook, NY, 2013, pp. 1454-1464.
31. J. Matousek, Lectures on Discrete Geometry, Springer, New York, 2002.
32. N. Nisan, Lower bounds for non-commutative computation, in STOC, ACM, New York, 1991, pp. 410-418.
33. M. Patrascu and R. Williams, On the possibility of faster SAT algorithms, in SODA, SIAM, Philadelphia, 2010, pp. 1065-1075.
34. J. Renegar, On the computational complexity and geometry of the first-order theory of the reals, J. Symbolic Comput., 13 (1992), pp. 255-352.
35. A. Seidenberg, A new decision method for elementary algebra, Ann. of Math. (2), 60 (1954), pp. 365-374.
36. A. Tarski, A Decision Method for Elementary Algebra and Geometry, University of California Press, Berkeley, CA, 1951.
37. W. Xu, X. Liu, and Y. Gong, Document clustering based on non-negative matrix factorization, in, SIGIR '03, ACM, New York, 2003, pp. 267-273.
38. S. Vavasis, On the complexity of nonnegative matrix factorization, SIAM J. Optim., 20 (2010), pp. 1364-1377.
39. M. Yannakakis, Expressing combinatorial optimization problems by linear programs, J. Com-put. System Sci., 43 (1991), pp. 441-466.