Is deep learning a useful tool for the pure mathematician?

Williamson, Geordie

doi:10.1090/bull/1829

Is deep learning a useful tool for the pure mathematician?
HTML articles powered by AMS MathViewer

by Geordie Williamson

Bull. Amer. Math. Soc. 61 (2024), 271-286

DOI: https://doi.org/10.1090/bull/1829

Published electronically: February 15, 2024

HTML | PDF | Request permission

Abstract:

A personal and informal account of what a pure mathematician might expect when using tools from deep learning in their research.

References

Charles Blundell, Lars Buesing, Alex Davies, Petar Veličković, and Geordie Williamson, Towards combinatorial invariance for Kazhdan-Lusztig polynomials, Represent. Theory 26 (2022), 1145–1191. MR 4510816, DOI 10.1090/ert/624
Callum R. Brodie, Andrei Constantin, Rehan Deen, and Andre Lukas, Machine learning line bundle cohomology, Fortschr. Phys. 68 (2020), no. 1, 1900087, 14. MR 4059246, DOI 10.1002/prop.201900087
Grant Barkley and Christian Gaetz, Combinatorial invariance for elementary intervals, Preprint, arXiv:2303.15577, (2023).
Grant T. Barkley and Christian Gaetz, Combinatorial invariance for lower intervals using hypercube decompositions, Sém. Lothar. Combin. 89B (2023), Art. 86, 8. MR 4659594
Rishi Bommasani, Drew A Hudson, Ehsan Adeli, Russ Altman, Simran Arora, Sydney von Arx, Michael S. Bernstein, Jeannette Bohg, Antoine Bosselut, Emma Brunskill, et al., On the opportunities and risks of foundation models, Preprint, arXiv:2108.07258, (2021).
Jiakang Bao, Yang-Hui He, Edward Hirst, Johannes Hofscheier, Alexander Kasprzyk, and Suvajit Majumder, Hilbert series, machine learning, and applications to physics, Phys. Lett. B 827 (2022), Paper No. 136966, 8. MR 4385221, DOI 10.1016/j.physletb.2022.136966
Mikhail Belkin, Daniel Hsu, Siyuan Ma, and Soumik Mandal, Reconciling modern machine-learning practice and the classical bias-variance trade-off, Proc. Natl. Acad. Sci. USA 116 (2019), no. 32, 15849–15854. MR 3997901, DOI 10.1073/pnas.1903070116
Francesco Brenti, Kazhdan-Lusztig polynomials: history problems, and combinatorial invariance, Sém. Lothar. Combin. 49 (2002/04), Art. B49b, 30. MR 2006565
Francesco Brenti, Kazhdan-Lusztig polynomials: history problems, and combinatorial invariance, Sém. Lothar. Combin. 49 (2002/04), Art. B49b, 30. MR 2006565
François Charton, Linear algebra with transformers, CoRR abs/2112.01898, (2021).
Francois Charton, Math with Transformers, https://www.youtube.com/watch?v=81o-Uiop5CA, October 2022, Accessed on 20 March, 2023.
Alex Davies, András Juhász, Marc Lackenby, and Nenad Tomasev, The signature and cusp geometry of hyperbolic knots, Geometry and Topology, (2022).
Alex Davies, Petar Veličković, Lars Buesing, Sam Blackwell, Daniel Zheng, Nenad Tomašev, Richard Tanburn, Peter Battaglia, Charles Blundell, András Juhász, Marc Lackenby, Geordie Williamson, Demis Hassabis, and Pushmeet Kohli, Advancing mathematics by guiding human intuition with AI, Nature 600 (2021), no. 7887, 70–74.
Ian Goodfellow, Yoshua Bengio, and Aaron Courville, Deep learning, Adaptive Computation and Machine Learning, MIT Press, Cambridge, MA, 2016. MR 3617773
Joel Gibson, Georg Gottwald, and Geordie Williamson, Machine Learning for the Working Mathematician, https://sites.google.com/view/mlwm-seminar-2022, June 2022, Accessed on 20 March, 2023.
Maxim Gurevich and Chuijia Wang, Parabolic recursions for Kazhdan–Lusztig polynomials and the hypercube decomposition, Preprint, arXiv:2303.09251 (2023).
Yang-Hui He and Minhyong Kim, Learning algebraic structures: Preliminary investigations, International Journal of Data Science in the Mathematical Sciences (2022), 1–20.
Kathryn Heal, Avinash Kulkarni, and Emre Can Sertöz, Deep learning Gauss-Manin connections, Adv. Appl. Clifford Algebr. 32 (2022), no. 2, Paper No. 24, 41. MR 4386394, DOI 10.1007/s00006-022-01207-1
Jesse Michael Han, Jason Rute, Yuhuai Wu, Edward W Ayers, and Stanislas Polu, Proof artifact co-training for theorem proving with language models, Preprint arXiv:2102.06203 (2021).
David H Hubel and Torsten N Wiesel, Receptive fields, binocular interaction and functional architecture in the cat’s visual cortex, The Journal of physiology 160 (1962), no. 1, 106.
Albert Q. Jiang, Sean Welleck, Jin Peng Zhou, Wenda Li, Jiacheng Liu, Mateja Jamnik, Timothée Lacroix, Yuhuai Wu, and Guillaume Lample, Draft, sketch, and prove: Guiding formal theorem provers with informal proofs, 2023.
Andrej Karpathy, Convnet Javascript Demo, https://cs.stanford.edu/people/karpathy/convnetjs/demo/classify2d.html, Accessed on 18 March, 2023.
Andrej Karpathy, A Recipe for Training Neural Networks, http://karpathy.github.io/2019/04/25/recipe/, Apr 25, 2019, Accessed on 20 March, 2023.
Yann LeCun, Léon Bottou, Yoshua Bengio, and Patrick Haffner, Gradient-based learning applied to document recognition, Proceedings of the IEEE 86 (1998), no. 11, 2278–2324.
Warren S. McCulloch and Walter Pitts, A logical calculus of the ideas immanent in nervous activity, Bull. Math. Biophys. 5 (1943), 115–133. MR 10388, DOI 10.1007/bf02478259
Marvin Minsky and Seymour A Papert, Perceptrons, reissue of the 1988 expanded edition with a new foreword by léon bottou: An introduction to computational geometry, MIT press, 2017.
David Mumford, The Astonishing Convergence of AI and the Human Brain, October 1, 2020, Accessed on 13 March, 2023.
Christopher Olah, Neural Networks, Manifolds, and Topology, https://colah.github.io/posts/2014-03-NN-Manifolds-Topology/, April 6, 2014, Accessed on 18 March, 2023.
Dylan James Peifer, Reinforcement Learning in Buchberger’s Algorithm, ProQuest LLC, Ann Arbor, MI, 2021. Thesis (Ph.D.)–Cornell University. MR 4297517
David E Rumelhart, Geoffrey E Hinton, and Ronald J Williams, Learning internal representations by error propagation, Tech. report, California Univ San Diego La Jolla Inst for Cognitive Science, 1985.
Daniel Smilkov and Shan Carter, The Tensorflow Playground, https://playground.tensorflow.org, Accessed on 18 March, 2023.
Carlos Simpson, Learning proofs for the classification of nilpotent semigroups, Preprint, arXiv:2106.03015, (2021).
A. M. Turing, Intelligent machinery, a heretical theory, Philos. Math. (3) 4 (1996), no. 3, 256–260. MR 1406760, DOI 10.1093/philmat/4.3.256
Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Lukasz Kaiser, and Illia Polosukhin, Attention is all you need, Advances in neural information processing systems 30 (2017).
Adam Zsolt Wagner, Constructions in combinatorics via neural networks, Preprint, arXiv:2104.14516, (2021).
Wikipedia, Universal approximation theorem, https://en.wikipedia.org/wiki/Universal_approximation_theorem, Accessed on 17 May, 2023.