Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
167 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
42 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Tensor-Networks-based Learning of Probabilistic Cellular Automata Dynamics (2404.11768v1)

Published 17 Apr 2024 in cond-mat.stat-mech, cs.LG, and quant-ph

Abstract: Algorithms developed to solve many-body quantum problems, like tensor networks, can turn into powerful quantum-inspired tools to tackle problems in the classical domain. In this work, we focus on matrix product operators, a prominent numerical technique to study many-body quantum systems, especially in one dimension. It has been previously shown that such a tool can be used for classification, learning of deterministic sequence-to-sequence processes and of generic quantum processes. We further develop a matrix product operator algorithm to learn probabilistic sequence-to-sequence processes and apply this algorithm to probabilistic cellular automata. This new approach can accurately learn probabilistic cellular automata processes in different conditions, even when the process is a probabilistic mixture of different chaotic rules. In addition, we find that the ability to learn these dynamics is a function of the bit-wise difference between the rules and whether one is much more likely than the other.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (20)
  1. OpenAI, https://chat.openai.com/chat (2024).
  2. M. Schuld, I. Sinayskiy, and F. Petruccione, An introduction to quantum machine learning, Contemporary Physics 56, 172 (2015).
  3. S. Cheng, L. Wang, and P. Zhang, Supervised learning with projected entangled pair states, Phys. Rev. B 103, 125117 (2021).
  4. X. Shi, Y. Shang, and C. Guo, Clustering using matrix product states, Phys. Rev. A 105, 052424 (2022).
  5. E. M. Stoudenmire, Learning relevant features of data with multi-scale tensor networks, Quantum Science and Technology 3, 034003 (2018).
  6. L. Deng and Y. Liu, Deep learning in natural language processing (Springer, 2018).
  7. A. Novikov, M. Trofimov, and I. Oseledets, Exponential machines (2017), arXiv:1605.03795 [stat.ML] .
  8. V. Pestun, J. Terilla, and Y. Vlassopoulos, Language as a matrix product state (2017), arXiv:1711.01416 [cs.CL] .
  9. T. Felser, S. Notarnicola, and S. Montangero, Efficient tensor network ansatz for high-dimensional quantum many-body problems, Phys. Rev. Lett. 126, 170603 (2021).
  10. U. Schollwöck, The density-matrix renormalization group, Rev. Mod. Phys. 77, 259 (2005).
  11. I. P. McCulloch, From density-matrix renormalization group to matrix product states, Journal of Statistical Mechanics: Theory and Experiment 2007, P10014 (2007).
  12. G. Vidal, Efficient simulation of one-dimensional quantum many-body systems, Phys. Rev. Lett. 93, 040502 (2004).
  13. U. Schollwöck, The density-matrix renormalization group in the age of matrix product states, Annals of Physics 326, 96 (2011), january 2011 Special Issue.
  14. M. Fannes, B. Nachtergaele, and R. F. Werner, Finitely correlated states on quantum spin chains, Communications in mathematical physics 144, 443 (1992).
  15. R. Orús, A practical introduction to tensor networks: Matrix product states and projected entangled pair states, Annals of physics 349, 117 (2014).
  16. S. Wolfram, Statistical mechanics of cellular automata, Rev. Mod. Phys. 55, 601 (1983).
  17. C. Guo, K. Modi, and D. Poletti, Tensor-network-based machine learning of non-markovian quantum processes, Phys. Rev. A 102, 062414 (2020).
  18. P.-Y. Louis and F. Nardi, Probabilistic Cellular Automata : Theory, Applications and Future Perspectives (2018).
  19. M. Cook, Universality in elementary cellular automata, Complex Systems 15 (2004).
  20. https://www.nscc.sg .

Summary

We haven't generated a summary for this paper yet.

X Twitter Logo Streamline Icon: https://streamlinehq.com