Provable bounds for learning some deep representations

31st International Conference on Machine Learning, ICML 2014

Volumn 1, Issue , 2014, Pages 883-891

  Arora, Sanjeev ^a   Bhaskara, Aditya ^b   Ge, Rong ^c   Ma, Tengyu ^a  

^a Princeton University   (United States)

^b GOOGLE INC   (United States)

^c MICROSOFT RESEARCH   (United Kingdom)

Author keywords

[No Author keywords available]

Indexed keywords

ARTIFICIAL INTELLIGENCE; COMPLEX NETWORKS; LEARNING SYSTEMS;

EDGE STRUCTURES; GENERATIVE MODEL; LAYER-WISE; MULTI-LAYER NETWORK; RANDOM EDGE WEIGHTS; RECOVERY PROCEDURE; RUNNING TIME; SAMPLE COMPLEXITY;

LEARNING ALGORITHMS;

EID: 84919790570     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (20)

1. Anandkumar, Anima, Foster, Dean P., Hsu, Daniel, Kakade, Sham M., and Liu, Yi-Kai. A spectral algorithm for latent Dirichlet allocation. In Advances in Neural In formation Processing Systems 25, 2012.
2. Arora, Sanjeev., Ge, Rong., and Moitra, Ankur. Learning topic models-going beyond svd. In IEEE 53rd Annual Symposium on Foundations of Computer Science, FOCS 2012, New Brunswick NJ, USA, October 20-23, pp. 1-10, 2012.
3. Arora, Sanjeev, Ge, Rong, and Moitra, Ankur. New algo rithms for learning incoherent and overcomplete dictio naries. ArXiv, 1308.6273, 2013.
4. Bengio, Yoshua. Learning deep architectures for AI. Foun dations and Trends in Machine Learning, 2(1): 1-127, 2009. Also published as a book. Now Publishers, 2009.
5. Bengio, Yoshua, Courville, Aaron C., and Vincent, Pascal. Representation learning: A review and new per spectives. IEEE Trans. Pattern Anal. Mack Intell., 35 (8): 1798-1828, 2013.
6. Berinde, R., Gilbert, A.C., Indyk, P., Karloff, H., and Strauss, M.J. Combining geometry and combinatorics: a unified approach to sparse signal recovery. In 46th An nual Allerton Conference on Communication, Control, and Computing, pp. 798-805, 2008.
7. Bondy, J Adrian and Hemminger, Robert L. Graph reconstructiona survey. Journal of Graph Theory, 1(3):227-268, 1977.
8. Cho, Youngmin and Saul, Lawrence. Kernel methods for deep learning. In Advances in Neural Information Pro cessing Systems 22, pp. 342-350. 2009.
9. Donoho, David L. Compressed sensing. Information Theory, IEEE Transactions on, 52(4): 1289-1306, 2006.
10. Hebb, Donald O. The Organization of Behavior: A Neu ropsychological Theory. Wiley, new edition edition, June 1949.
11. Hoory, Shlomo, Linial, Nathan, and Wigderson, Avi. Ex pander graphs and their applications. Bulletin of the American Mathematical Society, 43(4):439-561, 2006.
12. Hsu, Daniel and Kakade, Sham M. Learning mixtures of spherical gaussians: moment methods and spectral de compositions. In Proceedings of the 4th conference on Innovations in Theoretical Computer Science, pp. 11-20, 2013.
13. Hsu, Daniel, Kakade, Sham M., and Zhang, Tong. A spec tral algorithm for learning hidden Markov models. Jour nal of Computer and System Sciences, 78(5): 1460-1480, 2012.
14. Jackson, Jeffrey C, Klivans, Adam R, and Servedio, Rocco A. Learnability beyond ac0. In Proceedings of the thiry-fourth annual ACM symposium on Theory of computing, pp. 776-784. ACM, 2002.
15. Klivans, Adam R and Sherstov, Alexander A. Crypto graphic hardness for learning intersections of halfspaces. Journal of Computer and System Sciences, 75(1):2-12, 2009.
16. Krizhevsky, Alex, Sutskever, Ilya, and Hinton, Geoff. Imagenet classification with deep convolutional neural networks. In Advances in Neural Information Processing Systems 25, pp. 1106-1114. 2012.
17. Livni, Roi, Shalev-Shwartz, Shai, and Shamir, Ohad. A provably efficient algorithm for training deep networks. ArXiv, 1304.7045, 2013.
18. Moitra, Ankur and Valiant, Gregory. Settling the polyno mial learnability of mixtures of gaussians. In the 51st Annual Symposium on the Foundations of Computer Sci ence (FOCS), 2010.
19. Saxe, Andrew, Koh, Pang W, Chen, Zhenghao, Bhand, Maneesh, Suresh, Bipin, and Ng, Andrew. On random weights and unsupervised feature learning. In Proceedings of the 28th International Conference on Machine Learning (ICML-11), pp. 1089-1096, 2011.
20. Vincent, Pascal, Larochelle, Hugo, Bengio, Yoshua, and Manzagol, Pierre-Antoine. Extracting and composing robust features with denoising autoencoders. In ICML, pp. 1096-1103, 2008.