Sébastien Bubeck is a French-American computer scientist and mathematician. He is currently a Senior Principal Research Manager at Microsoft Research in the Machine Learning Foundations group and was formerly professor at Princeton University.[1] He is known for his contributions to online learning, optimization and more recently studying deep neural networks, and in particular transformer models.

Work

Bubeck's work spans a wide variety of topics in machine learning, theoretical computer science and artificial intelligence. Some of his most notable contributions include developing minimax rate for multi-armed bandits, linear bandits, developing an optimal algorithm for bandit convex optimization, and solving long-standing problems in k-server and metrical task systems. In regards to the mathematical theory of neural networks, Bubeck has both introduced and proved the law of robustness which links the number of parameters of a neural network and its regularity properties.[2][3] Bubeck has also made contributions to convex optimization, network analysis, and information theory. Bubeck's papers have over 15,000 citations to date.[4]

Prior to joining Microsoft Research, Bubeck was an assistant professor at Princeton University in the Department of Operations Research and Financial Engineering. He received his PhD from the Lille 1 University of Science and Technology, and also studied at the Ecole Normale Supérieure de Cachan.

Bubeck is the author of the book Convex optimization: Algorithms and complexity (2015).[5] He has also been on the editorial board of several scientific journals and conferences, including the Journal of the ACM[6] and Neural Information Processing Systems (NeurIPS) and was program committee chair for the 2018 Conference on Learning Theory (COLT)[7]

In 2023, Bubeck and his collaborators published a paper that claimed to observe "sparks of artificial general intelligence" in an early version of GPT-4, a large language model developed by OpenAI. The paper presented examples of GPT-4 performing tasks across various domains and modalities, such as mathematics, coding, vision, medicine, and law. The paper sparked wide interest and debate in the scientific community and the popular media, as it challenged the conventional understanding of learning and cognition in AI systems.[8][9][10][11][12][13] Bubeck also investigated the potential use of GPT-4 as an AI chatbot for medicine in a paper that evaluated the strengths, weaknesses, and ethical issues of relying on such a tool for medical purposes[14]

Honors and awards

Bubeck has received numerous honors and awards for his work, including the Alfred P. Sloan Research Fellowship in Computer Science in 2015,[15] and Best Paper Awards at the Conference on Learning Theory (COLT) in 2016,[16] Neural Information Processing Systems (NeurIPS) in 2018 and 2021 and in the ACM Symposium on Theory of Computing (STOC) 2023.[17][18] He has also received the Jacques Neveu prize for the best French PhD in Probability/Statistics,[19] the AI prize for a French PhD in Artificial Intelligence,[20] and the Gilles Kahn prize for a French PhD in Computer Science.[21]

Selected publications

  • Minimax policies for adversarial and stochastic bandits (2009), with Jean-Yves Audibert.
  • Best arm identification in multi-armed bandits (2010), with Jean-Yves Audibert and Rémi Munos.
  • Kernel-based methods for bandit convex optimization (2017), with Yin Tat Lee and Ronen Eldan.
  • A universal law of robustness via isoperimetry (2020), with Mark Sellke.
  • K-server via multiscale entropic regularization (2018), with Michael B. Cohen, Yin Tat Lee, James R. Lee, and Aleksander Madry.
  • Competitively chasing convex bodies (2019), with Yin Tat Lee, Yuanzhi Li, and Mark Sellke.
  • Regret analysis of stochastic and nonstochastic multi-armed bandit problems (2012), with Nicolò Cesa-Bianchi.

References

  1. "Sébastien Bubeck at Microsoft Research". Microsoft Research. Retrieved 2022-11-20.
  2. Rorvig, Mordechai (February 10, 2022). "Computer Scientists Prove Why Bigger Neural Networks Do Better". Quanta Maganize.
  3. Ananthaswamy, Anil (2023-03-08). "In AI, is bigger always better?". Nature. 615 (7951): 202–205. doi:10.1038/d41586-023-00641-w.
  4. "Sebastien Bubeck". scholar.google.com. Retrieved 2022-12-01.
  5. Bubeck, Sébastien (2015-11-01). "Convex Optimization: Algorithms and Complexity". Foundations and Trends in Machine Learning. 8 (3–4): 231–357. arXiv:1405.4980. doi:10.1561/2200000050. ISSN 1935-8237.
  6. "JOURNAL OF THE ACM Editorial Board". Journal of the ACM. Retrieved 2022-12-01.
  7. "dblp: COLT 2018". dblp.org. Retrieved 2022-12-01.
  8. Bubeck, Sébastien; Chandrasekaran, Varun; Eldan, Ronen; Gehrke, Johannes; Horvitz, Eric; Kamar, Ece; Lee, Peter; Lee, Yin Tat; Li, Yuanzhi; Lundberg, Scott; Nori, Harsha; Palangi, Hamid; Ribeiro, Marco Tulio; Zhang, Yi (2023-04-13). "Sparks of Artificial General Intelligence: Early experiments with GPT-4". arXiv:2303.12712 [cs.CL].
  9. Knight, Will. "Some Glimpse AGI in ChatGPT. Others Call It a Mirage". Wired. ISSN 1059-1028. Retrieved 2023-05-03.
  10. Sparks of AGI: early experiments with GPT-4, retrieved 2023-05-03
  11. Metz, Cade (2023-05-16). "Microsoft Says New A.I. Shows Signs of Human Reasoning". The New York Times. ISSN 0362-4331. Retrieved 2023-07-03.
  12. "ZEIT ONLINE | Lesen Sie zeit.de mit Werbung oder im PUR-Abo. Sie haben die Wahl". www.zeit.de. Retrieved 2023-07-03.
  13. "Greetings, People Of Earth". This American Life. 2023-06-15. Retrieved 2023-07-03.
  14. Lee, Peter; Bubeck, Sebastien; Petro, Joseph (2023-03-30). "Benefits, Limits, and Risks of GPT-4 as an AI Chatbot for Medicine". The New England Journal of Medicine. 388 (13): 1233–1239. doi:10.1056/NEJMsr2214184. ISSN 1533-4406. PMID 36988602. S2CID 257803472.
  15. "Bubeck Wins Sloan Research Fellowship". Operations Research & Financial Engineering. Retrieved 2022-11-20.
  16. "Program". easychair.org. Retrieved 2022-11-20.
  17. "NIPS 2018". nips.cc. Retrieved 2022-11-20.
  18. Chairs, Comms (30 November 2021). "Announcing the NeurIPS 2021 Award Recipients – NeurIPS Blog". Retrieved 2022-11-20.
  19. "2010". smai.emath.fr (in French). 2011-09-06. Retrieved 2022-11-20.
  20. adam, emmanuel (2022-05-03). "Lauréats des prix de thèse en Intelligence artificielle". AfIA (in French). Retrieved 2022-11-20.
  21. "Lauréat du prix de thèse SPECIF". SIF (in French). Retrieved 2022-11-20.
This article is issued from Wikipedia. The text is licensed under Creative Commons - Attribution - Sharealike. Additional terms may apply for the media files.