Jump to content

Draft:Aleksander Mądry

From Wikipedia, the free encyclopedia

Aleksander Mądry
Alma materMassachusetts Institute of Technology (PhD)
Scientific career
FieldsComputer Science
InstitutionsMassachusetts Institute of Technology
Thesis From Graphs to Matrices, and Back: New Techniques for Graph Algorithms  (2011)
Doctoral advisorMichel Xavier Goemans and Jonathan A. Kelner

Aleksander Madry is a Polish computer science professor at the Massachusetts Institute of Technology (MIT) and a principal investigator at MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL) who conducts research in the fields of algorithms, machine learning and optimization.

As of 2024 he is on leave at OpenAI leading preparedness team.[1][2][3]

Biography

[edit]

Aleksander Mądry was born in Wrocław, Poland and obtained a bachelor's degree in theoretical physics from the University of Wrocław. He continued his studies at the Massachusetts Institute of Technology with an M.S. in computer science ("Faster Generation of Random Spanning Trees") and a Ph.D. in 2011 [2] under the supervision of Michel Xavier Goemans and Jonathan A. Kelner ("From Graphs to Matrices, and Back: New Techniques for Graph Algorithms"). His dissertation was awarded the Association of Computing Machinery’s Doctoral Dissertation Award Honorable Mention.[4] and MIT’s George M. Sprowls Award for best thesis in computer science[5]

In 2015 he joined the MIT Electrical Engineering and Computer Science Department.

Research

[edit]

Aleksander Mądry's early work made substantial contributions to the theory of algorithms[6]. In 2011 he developed an approximation algorithm for the maximum flow problem, the first improvement in many years. And then, in 2013, he gave an exact calculation algorithm for the maximum flow problem which was the first to improve on the prior bound of Evan and Tarjan in 1975[7]. Mądry also contributed advances in the k-server problem and the traveling salesman problem [8]. The Pressburger Award wrote: "Aleksander’s results have been celebrated in the community not only because he broke long standing complexity barriers but moreover because he introduced new and very different techniques to the field which since have successfully been picked up by others."

Mądry's most recent work focuses on machine learning and artificial intelligence. In 2018 he developed a method of "adversarial training" to improve the robustness of machine learning models[9]. Since 2018 Mądry has extended his work to cover other areas of explaining why machine learning works, and investigating the role of data in the accuracy of machine learning models.

Mądry has testified to congress on the dangers of the use of machine learning.[10]

Awards

[edit]

References

[edit]
  1. ^ "How OpenAI Is Preparing For Future Safety Challenges". Forbes. Retrieved 2024-06-10.
  2. ^ Vynck, Gerrit De (2023-12-18). "OpenAI lays out plan for dealing with dangers of AI". Washington Post. ISSN 0190-8286. Retrieved 2024-06-10.
  3. ^ Metz, Rachel (December 18, 2023). "OpenAI Says Board Can Overrule CEO on Safety of New AI Releases". www.bloomberg.com. Retrieved 2024-06-10.
  4. ^ "Aleksander Madry". acm.org.
  5. ^ "Doing Machine Learning the Right Way". eecs.mit.edu.
  6. ^ "The Presburger Award 2018 Laudatio for Aleksander Madry" (PDF).
  7. ^ Madry, Aleksander (2013). "Navigating Central Path with Electrical Flows: From Flows to Matchings, and Back". 2013 IEEE 54th Annual Symposium on Foundations of Computer Science. pp. 253–262. arXiv:1307.2205. doi:10.1109/FOCS.2013.35. ISBN 978-0-7695-5135-7. S2CID 2324433. Retrieved 2024-03-04.
  8. ^ Asadpour, Arash; Goemans, Michel X.; Mądry, Aleksander; Gharan, Shayan Oveis; Saberi, Amin (2010-01-17). An O (log n /log log n )-approximation Algorithm for the Asymmetric Traveling Salesman Problem. Society for Industrial and Applied Mathematics. pp. 379–389. doi:10.1137/1.9781611973075.32. ISBN 978-0-89871-701-3.
  9. ^ Madry, Aleksander; Makelov, Aleksandar; Schmidt, Ludwig; Tsipras, Dimitris; Vladu, Adrian (2019-09-04), Towards Deep Learning Models Resistant to Adversarial Attacks, arXiv:1706.06083
  10. ^ "MIT professor to Congress: "We are at an inflection point" with AI". MIT News | Massachusetts Institute of Technology. 2023-03-10. Retrieved 2024-06-10.
[edit]


Category:Living people Category:Massachusetts Institute of Technology alumni