Learning Poisson Binomial Distributions

Algorithmica

Volumn 72, Issue 1, 2015, Pages 316-357

  Daskalakis, Constantinos ^a   Diakonikolas, Ilias ^b   Servedio, Rocco A ^c  

^a MASSACHUSETTS INSTITUTE OF TECHNOLOGY   (United States)

^b UNIVERSITY OF EDINBURGH   (United Kingdom)

^c Columbia University ^*  (United States)

Author keywords

Density estimation; Learning; Poisson binomial distribution

Indexed keywords

ALGORITHMS; FUZZY INFERENCE; LEARNING ALGORITHMS; RANDOM VARIABLES;

BINOMIAL DISTRIBUTION; CLASS OF DISTRIBUTIONS; DENSITY ESTIMATION; INDEPENDENT BERNOULLI RANDOM VARIABLES; LEARNING; PARAMETER GENERALIZATION; POISSON BINOMIAL DISTRIBUTIONS; SAMPLE COMPLEXITY;

POISSON DISTRIBUTION;

EID: 84939994905     PISSN: 01784617     EISSN: 14320541     Source Type: Journal    
DOI: 10.1007/s00453-015-9971-3     Document Type: Article

References (55)

1. Acharya, J., Jafarpour, A., Orlitsky, A., Suresh, A.T.: Sorting with adversarial comparators and application to density estimation. In: the IEEE International Symposium on Information Theory (ISIT) (2014)
2. Berry, Andrew C.: The accuracy of the Gaussian approximation to the sum of independent variates. Trans. Am. Math. Soc. 49(1), 122–136 (1941)
3. Barbour, A.D., Holst, L., Janson, S.: Poisson Approximation. Oxford University Press, New York (1992)
4. Birgé, L.: Estimating a density under order restrictions: nonasymptotic minimax risk. Ann. Stat. 15(3), 995–1012 (1987)
5. Birgé, L.: On the risk of histograms for estimating decreasing densities. Ann. Stat. 15(3), 1013–1022 (1987)
6. Birgé, L.: Estimation of unimodal densities without smoothness assumptions. Ann. Stat. 25(3), 970–981 (1997)
7. Barbour, A.D., Lindvall, T.: Translated Poisson approximation for Markov chains. J. Theor. Probab. 19(3), 609–630 (2006)
8. Brent, R.P.: Multiple-precision zero-finding methods and the complexity of elementary function evaluation. In: Traub, J.F. (ed.) Analytic Computational Complexity, pp. 151–176. Academic Press, New York (1975)
9. Brent, R.P.: Fast multiple-precision evaluation of elementary functions. J. ACM 23(2), 242–251 (1976)
10. Belkin, M., Sinha, K.: Polynomial learning of distribution families. In: FOCS, pp. 103–112 (2010)
11. Le Cam, L.: An approximation theorem for the Poisson binomial distribution. Pac. J. Math. 10, 1181–1197 (1960)
12. Chan, S., Diakonikolas, I., Servedio, R., Sun, X.: Learning mixtures of structured distributions over discrete domains. In: SODA, pp. 1380–1394 (2013)
13. Chernoff, H.: A measure of asymptotic efficiency for tests of a hypothesis based on the sum of observations. Ann. Math. Stat. 23, 493–507 (1952)
14. Chen, L.H.Y.: On the convergence of Poisson binomial to Poisson distributions. Ann. Probab. 2, 178–180 (1974)
15. Chen, S.X., Liu, J.S.: Statistical applications of the Poisson-binomial and conditional Bernoulli distributions. Stat. Sinica 7, 875–892 (1997)
16. Daskalakis, C.: An efficient PTAS for two-strategy anonymous games. In: WINE 2008, pp. 186–197. Full version available as ArXiV report (2008)
17. Daskalakis, C., Diakonikolas, I., O’Donnell, R., Servedio, R., Tan, L.-Y.: Learning sums of independent integer random variables. In: FOCS (2013)
18. Daskalakis, C., Diakonikolas, I., Servedio, R.: Learning Poisson binomial distributions. In: STOC, pp. 709–728 (2012)
19. Daskalakis, C., Diakonikolas, I., Servedio, R.A.: Learning $$k$$k-modal distributions via testing. In: SODA, pp. 1371–1385 (2012)
20. Daskalakis, C., Kamath, G.: Faster and sample near-optimal algorithms for proper learning mixtures of gaussians. In: the 27th Conference on Learning Theory (COLT) (2014)
21. Devroye, L., Lugosi, G.: Nonasymptotic universal smoothing factors, kernel complexity and Yatracos classes. Ann. Stat. 25, 2626–2637 (1996)
22. Devroye, L., Lugosi, G.: A universally acceptable smoothing factor for kernel density estimation. Ann. Stat. 24, 2499–2512 (1996)
23. Devroye, L., Lugosi, G.: Combinatorial Methods in Density Estimation, Springer Series in Statistics. Springer, Berlin (2001)
24. Deheuvels, P., Pfeifer, D.: A semigroup approach to Poisson approximation. Ann. Probab. 14, 663–676 (1986)
25. Dubhashi, D., Panconesi, A.: Concentration of Measure for the Analysis of Randomized Algorithms. Cambridge University Press, Cambridge (2009)
26. Daskalakis, C., Papadimitriou, C.: On oblivious PTAS’s for Nash equilibrium. In: STOC 2009, pp. 75–84. Full version available as ArXiV report (2011)
27. Daskalakis, C., Papadimitriou, C.: Sparse covers for sums of indicators. Arxiv Report (2013) http://arxiv.org/abs/1306.1265
28. Ehm, Werner: Binomial approximation to the Poisson binomial distribution. Stat. Probab. Lett. 11, 7–16 (1991)
29. Esseen, Carl-Gustav: On the Liapunoff limit of error in the theory of probability. Arkiv för matematik, astronomi och fysik A, 1–19 (1942)
30. Fillebrown, Sandra: Faster computation of Bernoulli numbers. J. Algorithms 13(3), 431–445 (1992)
31. Hodges, S.L., Le Cam, L.: The Poisson approximation to the binomial distribution. Ann. Math. Stat. 31, 740–747 (1960)
32. Hoeffding, W.: Probability inequalities for sums of bounded random variables. J. Am. Stat. Assoc. 58, 13–30 (1963)
33. Johnson, J.L.: Probability and Statistics for Computer Science. Wiley, New York (2003)
34. Keilson, J., Gerber, H.: Some results for discrete unimodality. J. Am. Stat. Assoc. 66(334), 386–389 (1971)
35. Kearns, M., Mansour, Y., Ron, D., Rubinfeld, R., Schapire, R., Sellie, L.: On the learnability of discrete distributions. In: Proceedings of the 26th Symposium on Theory of Computing, pp. 273–282 (1994)
36. Kalai, A.T., Moitra, A., Valiant, G.: Efficiently learning mixtures of two Gaussians. In: STOC, pp. 553–562 (2010)
37. Knuth, Donald E.: The Art of Computer Programming, Volume II: Seminumerical Algorithms, 2nd edn. Addison-Wesley, Boston (1981)
38. Mikhailov, V.G.: On a refinement of the central limit theorem for sums of independent random indicators. Theory Probab. Appl. 38, 479–489 (1993)
39. Moitra, A., Valiant, G.: Settling the polynomial learnability of mixtures of Gaussians. In: FOCS, pp. 93–102 (2010)
40. Kotz, S., Johnson, N.L., Kemp, A.W.: Univariate Discrete Distributions. Wiley, New York (2005)
41. Poisson, S.D.: Recherches sur la Probabilitè des jugements en matié criminelle et en matiére civile. Bachelier, Paris (1837)
42. Peres, Y., Watson, S.: Personal communication (2011)
43. Röllin, A.: Translated Poisson approximation using exchangeable pair couplings. Ann. Appl. Probab. 17(5/6), 1596–1614 (2007)
44. Roos, B.: Binomial approximation to the Poisson binomial distribution: the Krawtchouk expansion. Theory Probab. Appl. 45, 328–344 (2000)
45. Salamin, Eugene: Computation of pi using arithmetic-geometric mean. Math. Comput. 30(135), 565–570 (1976)
46. Sato, Ken-Iti: Convolution of unimodal distributions can produce any number of modes. Ann. Probab. 21(3), 1543–1549 (1993)
47. Suresh, A.T., Orlitsky, A., Acharya, J., Jafarpour, A.: Near-optimal-sample estimators for spherical gaussian mixtures. In: the Annual Conference on Neural Information Processing Systems (NIPS) (2014)
48. Soon, S.Y.T.: Binomial approximation for dependent indicators. Stat. Sin. 6, 703–714 (1996)
49. Schönhage, A., Strassen, V.: Schnelle multiplikation grosser zahlen. Computing 7, 281–292 (1971)
50. Steele, J.M.: Le Cam’s inequality and Poisson approximation. Am. Math. Monthly 101, 48–54 (1994)
51. Volkova, AYu.: A refinement of the central limit theorem for sums of independent random indicators. Theory Probab. Appl. 40, 791–794 (1995)
52. Valiant, G., Valiant, P.: Estimating the unseen: an $$n/\log (n)$$n/log(n)-sample estimator for entropy and support size, shown optimal via new CLTs. In: STOC, pp. 685–694 (2011)
53. Wang, Y.H.: On the number of successes in independent trials. Stat. Sin. 3, 295–312 (1993)
54. Whittaker, E.T.: A course of modern analysis. Cambridge University Press, Cambridge (1980)
55. Yatracos, Y.G.: Rates of convergence of minimum distance estimators and Kolmogorov’s entropy. Ann. Stat. 13, 768–774 (1985)