Raphael Arkady Meyer

I am a \(2^{nd}\) year Ph.D. Student at NYU Tandon School of Engineering, advised by Prof. Christopher Musco and part of the Algorithms and Foundations Group.

I research the interplay of theoretical statistics and computation, largely through the lens of linear algebra.

Links: Google Scholar, dblp, Github, Zoom Room, NYU Tandon

My recent publications have looked at:

• Provably Optimal Fast Linear-Algebra Algorithms (SOSA2021)

• The Statistical Complexity of Kernel Learning (NeurIPS2020, ICML2019)

Of course, I am interested in problems beyond these areas, and if you want to work with me on a problem, send me an email: \(ram900@nyu.edu\)

Publications

1. Hutch++: Optimal Stochastic Trace Estimation^[1]

   with Cameron Musco, Christopher Musco, David P. Woodruff

   at Symposium on Simplicity in Algorithms (SOSA 2021)

2. The Statistical Cost of Robust Kernel Hyperparameter Turning

   with Christopher Musco

   at Advances in Neural Information Processing Systems (NeurIPS 2020)

3. Optimality Implies Kernel Sum Classifiers are Statistically Efficient

   with Jean Honorio

   at International Conference on Machine Learning (ICML 2019)

4. Characterizing Optimal Security and Round-Complexity for Secure OR Evaluation

   with Amisha Jhanji, Hemanta K. Maji

   at IEEE International Symposium on Information Theory (ISIT 2017)

Teaching

I really enjoy teaching, and have been a TA for a few courses now:

• Algorithmic Machine Learning and Data Science, New York University, Fall 2020

• Introduction to Machine Learning, New York University, Spring 2020

• Introduction to the Analysis of Algorithms, Purdue University, Fall 2018