Abstract
The paper analyzes current research and the state of the industry to assess the complexity of machine learning algorithms. The tasks of deep learning are associated with an extremely high degree of computational complexity, which requires the use, first of all, of new algorithmic methods and an understanding of the assessment of the complexity of the calculations. This area of research is not given due attention for various reasons, but primarily because of the novelty of this paradigm, as well as the use of other advanced methods, which is briefly analyzed in this paper.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
- 2.
- 3.
- 4.
- 5.
- 6.
- 7.
- 8.
- 9.
- 10.
- 11.
References
Mohri, M., Rostamizadeh, A., Talwalkar, A.: Foundations of Machine Learning, p. 427. The MIT Press, Cambridge, Massachusetts, London, England (2012)
Knuth D.E.: The Art of Computer Programming. 3rd ed. vol 1. Addison-Wesley (2013) 672pp
Knuth, E.D.: The Art of Computer Programming, Seminumerical Algorithms, 3rd edition ed., vol 2. Addison-Wesley, 762pp
Graham, R.L., Knuth, D.E., Patashnik, O.: Concrete Mathematics. 2nd ed. Addison-Wesley Publishing Company (1994) 604pp
Cormen, T.H., Leiserson, C.E., Rivest, R.L.: Introduction to Algorithms, 3rd ed. The MIT Press, 1292pp
Sedgewick, R., Wayne, K.: Algorithms. Addison-Wesley (2013), 848pp
Dasgupta, S.: Algorithms, 1st ed. McGraw-Hill Education, 336pp
Knuth, D.E.: The Art of Computer Programming. Generating All Trees-History of Combinatorial Generation, vol. 4 (2007), 160pp
Rieck, B., Togninalli, M., Bock, C., Moor, M.: Neural persistence: a complexity measure for deep neural networks using algebraic topology. ICLR (2019)
Williamson, D.P., Shmoys, D.B.: The Design Approximation Algorithms. Cambridge University Press (2010)
Бopecкoв, A.B., Xapлaмoв, A.A., Mapкoвcкий, H.Д., Mикyшин, Д.H., Mpoтникoв, E.B., Mыльцeв, A.A., Caxapныx, H.A., Фpoлoв, B.A.: Пapaллeльныe вычиcлeния нa GPU. Apxитeктypa и пpoгpaммнaя мoдeль CUDA, Издaтeльcтвo Mocкoвcкoгo yнивepcитeтa (2012)
Graham, R.L., Knuth, D.E., Patashnik, O.: Concrete Mathematics. Reading. Addison-Wesley Publishing Company, Inc., Massachusetts (1994, 1989), 604pp
Li, L., Abu-Mostafa, Y.S.: Data Complexity in Machine Learning, Caltech Computer Science Technical Report CaltechCSTR:2006.004, May 2006 (2006)
Widrow, B.: Adaptive Signal Processing, 1st ed. (1985), 486pp
Bengio, Y.: Learning Deep Architectures for AI, Technical Report 1312. [Online]. https://www.iro.umontreal.ca/~lisa/pointeurs/TR1312.pdf
Bengio, Y., LeCun, Y.: Scaling Learning Algorithms towards AI. In: Large-Scale Kernel Machines, P. 408. The MIT Press (2007)
Barron, A.R.: Approximation and estimation bounds for artificial neural network. Mach. Learn. 14, 115–133 (1994)
Hassibi, B., Stork, D.G.: Second order derivatives for network pruning: optimal brain surgeon. Adv. Neural Inf. Proc. Syst. 5(NIPS 1992) (1992)
Bengio, Y., Lamblin, P., Popovici, D., Larochelle, H.: Greedy layer-wise training of deep networks. https://papers.nips.cc/paper/3048-greedy-layer-wise-training-of-deep-networks.pdf (дaтa oбpaщeния: 15.09.2019)
Justus, D., Brennan, J., Bonner, S., McGough, A.S.: Predicting the computational cost of deep learning models. https://arxiv.org/pdf/1811.11880.pdf (дaтa oбpaщeния: 1.11.2019)
Scholkopf, B., Christopher, Smola, A.J.: Advances in Kernel Methods. The MIT Press (1999)
Corinna Cortes, Vladimir Vapnik. Support-Vector Networks. http://homepages.rpi.edu/ ~ bennek/class/mmld/papers/svn.pdf (дaтa oбpaщeния: 02.10.2019)
Dall’Anese, E., Simonetto, A., Becker, S., Madden, L.: Optimization and Learning with Information Streams: Time-varying Algorithms and Applications. https://arxiv.org/pdf/1910.08123v1.pdf (дaтa oбpaщeния: 22.10.2019)
Colin, I., Dos Santos, L., Scaman, K.: Theoretical limits of pipeline parallel optimization and application to distributed deep learning http://arxiv-sanity.com/search?q = learning+and+optimization (дaтa oбpaщeния: 15.10.2019)
Liu, S., Vicente, L.N.: The stochastic multi-gradient algorithm for multi-objective The stochastic multi-gradient algorithm for multi-objective. https://arxiv.org/pdf/1907.04472v2.pdf (дaтa oбpaщeния: 28.09.2019)
Backurs, A., Indyk, P., Schmidt, L.: On the fine-grained complexity of empirical risk minimization:kernel methods and neural networks. https://papers.nips.cc/paper/7018-on-the-fine-grained-complexity-of-empirical-risk-minimization-kernel-methods-and-neural-networks.pdf (дaтa oбpaщeния: 02.10.2019)
Shalev-Shwartz, S., Ben-David, S.: Understanding Machine Learning. Cambridge University Press, From Theory to Algorithms (2014)
Fujimoto, S., Conti, E., Ghavamzadeh, M., Pineau, J.: Benchmarking Batch Deep Reinforcement Learning Algorithms. https://arxiv.org/pdf/1910.01708v1.pdf (дaтa oбpaщeния: 10.7.2019)
Glasser, I., Sweke, R., Pancotti, N., Eisert, J., Cirac, J.I.: Expressive power of tensor-network factorizations for probabilistic modeling. https://arxiv.org/pdf/1907.03741v1.pdf (дaтa oбpaщeния: 03.10.2019)
Sheriff, M.R., Chatterjee, D.: Dictionary Learning With Almost Sure Error Constraints. https://arxiv.org/pdf/1910.08828v1.pdf (дaтa oбpaщeния: 10.17.2019)
Jungnickel, D.: Graphs, Networks and Algorithms. 3rd ed. Springer (2008)
Acknowledgements
We thank the staff of SPbPU Peter the Great and the Institute of Computer Science and Technology for their support in the preparation of this material. We drew thoughts and ideas at joint seminars within the framework of the institute, as well as during fruitful communication with colleagues.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Baskakov, D., Arseniev, D. (2021). On the Computational Complexity of Deep Learning Algorithms. In: Voinov, N., Schreck, T., Khan, S. (eds) Proceedings of International Scientific Conference on Telecommunications, Computing and Control. Smart Innovation, Systems and Technologies, vol 220. Springer, Singapore. https://doi.org/10.1007/978-981-33-6632-9_30
Download citation
DOI: https://doi.org/10.1007/978-981-33-6632-9_30
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-33-6631-2
Online ISBN: 978-981-33-6632-9
eBook Packages: EngineeringEngineering (R0)