Noah Golowich


Links:
Google Scholar
Twitter

I am a 1st year PhD student at MIT, working on theoretical machine learning. I am very fortunate to be advised by Constantinos Daskalakis.

I am grateful to be supported by a Hertz Foundation Fellowship, an NSF Graduate Fellowship, and an MIT Akamai Fellowship.

Contact information:
n$g at mit dot edu, replace the $ with z
CSAIL
MIT EECS
32 Vassar Street
Cambridge, MA 02139

Papers

Preprints
  • Noah Golowich, Sarath Pattathil, Constantinos Daskalakis, and Asuman Ozdaglar. Last iterate is slower than averaged iterate in smooth convex-concave saddle point problems. arXiv:2002.00057
  • Badih Ghazi, Noah Golowich, Ravi Kumar, Pasin Manurangsi, Rasmus Pagh, and Ameya Velingker. Pure differentially private summation from anonymous messages. arXiv:2002.01919.
  • Badih Ghazi, Noah Golowich, Ravi Kumar, Rasmus Pagh, and Ameya Velingker. On the power of multiple anonymous messages. arXiv:1908.11358.
    • Slides for my talk at the MIT Cryptography and Information Security (CIS) seminar, December 2019: pdf.
Publications
  • Noah Golowich and Madhu Sudan. Round complexity of common randomness generation: the amortized setting. arXiv.
    • In 2020 Symposium on Discrete Algorithms: SODA 2020.
    • Slides for my SODA talk, January 2020: ppt, pdf.
  • Sanjeev Arora, Nadav Cohen, Noah Golowich, and Wei Hu. A convergence analysis of gradient descent for deep linear neural networks. arXiv.
    • In 7th International Conference on Learning Representations: ICLR 2019.
  • Mitali Bafna, Badih Ghazi, Noah Golowich, and Madhu Sudan. Communication-rounds tradeoffs for common randomness and secret key generation. arXiv.
    • In Proceedings of the 2019 Symposium on Discrete Algorithms: SODA 2019.
    • Slides for my SODA talk, January 2019: pdf.
  • Paul Dütting, Zhe Feng, Noah Golowich, Harikrishna Narasimhan, and David C. Parkes. Machine learning for optimal economic design.
  • Noah Golowich, Harikrishna Narasimhan, and David C. Parkes. Deep learning for multi-facility location mechanism design.
    • In 27th International Joint Conference on Artificial Intelligence: IJCAI 2018.
  • Noah Golowich, Alexander Rakhlin, and Ohad Shamir. Size-independent sample complexity of neural networks. arXiv.
  • Noah Golowich. Coloring chains for compression with uncertain priors. arXiv.
  • Noah Golowich. The m-degenerate chromatic number of a digraph. arXiv.
  • Noah Golowich and David Rolnick. Acyclic subgraphs of planar digraphs. arXiv.
  • Noah Golowich. Resolving a conjecture on degree of regularity of linear homogeneous equations. arXiv.
  • Kavish Gandhi, Noah Golowich, and László M. Lovász. Degree of regularity of linear homogeneous equations. arXiv.
Site design from Vasilios Mavroudis : Plain Academic