On the difficulty of approximately maximizing agreements

Journal of Computer and System Sciences

Volumn 66, Issue 3, 2003, Pages 496-514

  Ben David, Shai ^a   Eiron, Nadav ^b   Long, Philip M ^c  

^a TECHNION ISRAEL INSTITUTE OF TECHNOLOGY   (Israel)

^b IBM ALMADEN RESEARCH CENTER   (United States)

^c GENOME INSTITUTE OF SINGAPORE   (Singapore)

Author keywords

Axis aligned hyper rectangles; Balls; Computational learning theory; Half spaces; Hardness; Inapproximability; Machine learning; Monomials; Neural networks

Indexed keywords

COMPUTATIONAL COMPLEXITY; LEARNING SYSTEMS; NEURAL NETWORKS; POLYNOMIALS; THEOREM PROVING;

AXIS-ALIGNED HYPER-RECTANGLES; MONOMIALS;

APPROXIMATION THEORY;

EID: 0038575680     PISSN: 00220000     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0022-0000(03)00038-2     Document Type: Article

References (24)

1. E. Amaldi, V. Kann, The complexity and approximability of finding maximum feasible subsystems of linear relations, Theoret. Comput. Sci. 147 (1995) 181-210.
2. D. Angluin, P.D. Laird, Learning from noisy examples, Mach. Learning 2 (1988) 343-370.
3. S. Arora, L. Babai, J. Stern, Z. Sweedyk, Hardness of approximate optima in lattices, codes, and linear systems, J. Comput. System Sci. 54 (2) (1997) 317-331.
4. P. Bartlett, S. Ben-David, Hardness results for neural network approximation problems, The 1999 IMA European Conference on Computational Learning Theory, 1999, pp. 50-62.
5. S. Ben-David, N. Eiron, H.U. Simon, On the hardness of unsupervised learning, 2000, to appear.
6. A.L. Blum, R.L. Rivest, Training a 3-node neural network is NP-complete, Neural Networks 5 (1) (1992) 117-127.
7. A. Blumer, A. Ehrenfeucht, D. Haussler, M.K. Warmuth, Learnability and the Vapnik-Chervonenkis dimension, J. Assoc. Comput. Mach. 36 (4) (1989) 929-965.
8. B. DasGupta, H.T. Siegelmann, Eduardo D. Sontag, On the complexity of training neural networks with continuous activation functions, IEEE Trans. Neural Networks 6 (6) (1995) 1490-1504.
9. D.P. Dobkin, D. Gunopulos, W. Maass, Computing the maximum bichromatic discrepancy, with applications in computer graphics and machine learning, J. Comput. System Sci. 52 (3) (1996) 453-470.
10. U. Feige, A threshold of log n for approximating set cover, Proceedings of the 28th Annual ACM Symposium on Theory of Computing, Philadelphia, PA, 1996, pp. 314-318.
11. Y. Freund, R.E. Schapire, A decision-theoretic generalization of on-line learning and an application to boosting, Proceedings of the Second European Conference on Computational Learning Theory, Barcelona, Spain, 1995, pp. 23-37.
12. Y. Freund, R. Schapire, Experiments with a new boosting algorithm, Proceedings of the Thirteenth International Conference on Machine Learning, Bari, Italy, 1996.
13. J. Håstad, Some optimal inapproximability results, Proceedings of the 29th ACM Symposium on the Theory of Computing, El Paso, TX, 1997, pp. 1-10.
14. D. Haussler, Decision theoretic generalizations of the PAC model for neural net and other learning applications, Inform. Comput. 100 (1) (1992) 78-150.
15. D.P. Helmbold, P.M. Long, Tracking drifting concepts by minimizing disagreements, Mach. Learning 14 (1) (1994) 27-46.
16. K.U. Höffgen, H.U. Simon, K.S. Van Horn, Robust trainability of single neurons, J. Comput. System Sci. 50 (1) (1995) 114-125.
17. J.S. Judd, Neural Network Design and the Complexity of Learning, MIT Press, Cambridge, MA, 1990.
18. M. Kearns, M. Li, Learning in the presence of malicious errors, SIAM J. Comput. 22 (4) (1993) 807-837.
19. M. Kearns, L. Valiant, Cryptographic limitations on learning boolean formulae and finite automata, J. Assoc. Comput. Mach. 41 (1) (1994) 67-95.
20. M.J. Kearns, R.E. Schapire, L.M. Sellie, Toward efficient agnostic learning, Mach. Learning 17 (1994) 115-141.
21. M. Kharitonov, Cryptographic hardness of distribution specific learning, Proceedings of the 25th ACM Symposium on the Theory of Computing, San Diego, CA, 1993, pp. 372-381.
22. C. Kuhlmann, Hardness results for general two-layer neural networks, Proceedings of the 2000 Conference on Computational Learning Theory, Palo Alto, CA, 2000, pp. 275-285.
23. L. Pitt, L.G. Valiant, Computational limitations on learning from examples, J. Assoc. Comput. Mach. 35 (4) (1988) 965-984.
24. R. Schapire, The strength of weak learnability, Mach. Learning 5 (1990) 197-227.