Avatar

David Cheikhi

PhD Candidate Columbia University, Graduate School of Business
email: dc3430 (at) gsb (dot) columbia (dot) edu

I am a second year PhD candidate in the Decision, Risk and Operations Division of the Graduate School of Business at Columbia University. I am advised by Professor Dan Russo. Prior to joining Columbia, I earned an MS in Computer Science from Columbia University and got my Bachelors in Applied Maths and Computer Science from Ecole Polytechnique (Paris).

I am broadly interested in Reinforcement Learning, Data Driven Decision Making and online optimization.

Research

Refereed Conferences

On the Limited Representational Power of Value Functions and its Links to Statistical (In)Efficiency with Dan Russo. Under submission.

On the Statistical Benefit of Temporal Difference Learning with Dan Russo. ICML 2023, oral .

Stochastic Flows and Geometric Optimization on the Orthogonal Group
with K. Choromanski, J. Davis, V. Likhosherstov, A. Nazaret, A. Bahamou, X. Song, M. Akarte, J. Parker-Holder, J. Bergquist, Y. Gao, A. Pacchiano, T. Sarlos, A. Weller, V. Sindhwani. ICML 2020.

Teaching

Teaching Assistant

Columbia Business School

  • PhD Core: Foundations of Statistical Modeling Spring 2023
  • MBA Core: Managerial Statistics. Fall 2022
  • MBA Elective: Sports Analyticcs. Summer 2022, Fall 2022

Columbia Engineering School

  • Analysis of Algorithms. Fall 2020
  • Randomized Algorithms. Fall 2019