Lee Cohen

About

I'm a postdoctoral researcher at Stanford, hosted by Omer Reingold. Previously, I was a Research Assistant Professor at Toyota Technological Institute at Chicago (TTIC). I completed my PhD in Computer Science at Tel Aviv University, where I was very fortunate to be advised by Yishay Mansour.

My research lies at the intersection of learning theory and societal challenges. In particular, I develop methodologies to address fairness, incentive awareness, personalization, and explainability in machine learning and decision-making.

Email: leecohencs AT gmail DOT com

DBLP, Google Scholar

News

• Aug 2023:  Avrim Blum and I are organizing DavidFest & YishayFest: Celebratory/milestone birthday workshops in honor of David McAllester and Yishay Mansour at TTIC! 

• 2021: Check out our WiML-T event at COLT 2021!

• Oct 2020: Interested in ML theory & identify yourself as a woman?  You can sign up for our mentorship program for women in machine learning theory either as a mentor, mentee, or both!

• Feb-Mar 2020: Visiting Efficient Algorithms research group, TU Berlin

Publications 

• Probably Approximately Precision and Recall Learning

Lee Cohen,  Yishay Mansour, Shay Moran, and Han Shao

Conference on Neural Information Processing Systems (NeurIPS) 2025

[arxiv]

• Two Tickets are Better than One: Fair and Accurate Hiring Under Strategic LLM Manipulations

Lee Cohen, Connie Hong, Jack Hsieh, and Judy Shen

International Conference on Machine Learning (ICML) 2025

[arxiv]

• Bayesian Strategic Classification

Lee Cohen, Saeed Sharifi-Malvajerdi, Kevin Stangl, Ali Vakilian, and Juba Ziani

Conference on Neural Information Processing Systems (NeurIPS) 2024

[arxiv]

• Learnability Gaps of Strategic Classification

Lee Cohen,  Yishay Mansour, Shay Moran, and Han Shao

Conference on Learning Theory (COLT) 2024

[arxiv]

• Incentivized Collaboration in Active Learning

Lee Cohen and Han Shao

Symposium on Foundations of Responsible Computing (FORC) 2024

[arxiv]

• Eliciting User Preferences for Personalized Multi-Objective Decision Making through Comparative Feedback

Han Shao, Lee Cohen, Avrim Blum, Yishay Mansour, Aadirupa Saha, and Matthew R Walter

Conference on Neural Information Processing Systems (NeurIPS) 2023

[arxiv]

• Finding Safe Zones of Markov Decision Processes Policies

Lee Cohen,  Yishay Mansour, and  Michal Moshkovitz

Conference on Neural Information Processing Systems (NeurIPS) 2023

[arxiv]

• Sequential Strategic Screening

Lee Cohen*, Saeed Sharifi-Malvajerdi*, Kevin Stangl*, Ali Vakilian*, and Juba Ziani*

International Conference on Machine Learning (ICML) 2023

[arxiv]

• Modeling Attrition in Recommender Systems with Departing Bandits

Omer Ben-Porat*,  Lee Cohen*,  Liu Leqi*,  Zachary C. Lipton , and Yishay Mansour

Oral presentation, AAAI Conference on Artificial Intelligence (AAAI) 2022 (Oral)

[arXiv]

• Dueling Bandits with Team Comparisons

Lee Cohen*,  Ulrike Schmidt-Kraepelin* and Yishay Mansour

Conference on Neural Information Processing Systems (NeurIPS) 2021

[arxiv]

• Sample Complexity of Uniform Convergence for Multicalibration 

Eliran Shabat*,  Lee Cohen*,  and Yishay Mansour

Conference on Neural Information Processing Systems (NeurIPS) 2020 

[arxiv]

• Efficient Candidate Screening under Multiple Tests and Implications for Fairness  

Lee Cohen,  Zachary C. Lipton, and Yishay Mansour

Symposium on Foundations of Responsible Computing (FORC) 2020

[arxiv]

• Optimal Algorithm for Bayesian Incentive-Compatible Exploration

Lee Cohen and Yishay Mansour

ACM Conference on Economics and Computation (EC) 2019

[arxiv]

* Equal contribution. 

Preprints

• Utilizing Adversarial Examples for Bias Mitigation and Accuracy Enhancement

Pushkar Shukla, Dhruv Srikanth, Lee Cohen, Matthew Turk

arxiv, 2024

Teaching

• Spring 19/20: Reinforcement Learning (Teaching Assistant)

• Spring 18/19: Reinforcement Learning (Teaching Assistant)

• Fall 18/19: Advanced topics in ML and AGT (Graduate level course, grader)