I am an assistant professor of Computer Science at the Technion. My research lies at the intersection of machine learning and human behavior, including topics such as:
– Modeling and predicting human behavior and social dynamics
– Learning to support human decision-making
– Strategic classification and performative prediction
– Training for human objectives and with humans in the loop
– Implications of deploying predictive models in social contexts
I am looking for strong, curious students interested in conducting research at the intersection of machine learning and human behavior.
Before joining the Technion, I was a postdoc at the School of Engineering and Applied Sciences (SEAS) at Harvard, working with David Parkes and Yaron Singer. I was also a fellow of the Center for Research on Computation and Society (CRCS) and of the Harvard Data Science Initiative (HDSI). I received my BSc (CS and psych), MA (CS), and PhD (CS) from the Hebrew University of Jerusalem, where I was advised by Amir Globerson. I was also a long-term research intern at Microsoft Research in Israel working with Elad Yom-Tov and Yishay Mansour.
email: nirr at cs dot technion dot ac dot il
Teaching:
– [236756] Introduction to Machine Learning (Spring 2021-2024)
– [236608] Machine Learning and Human Behavior (Winter 2021-2023)
– [236802] Seminar: Failures Modes in Machine Learning (Spring 2022-2024)
Tutorials:
Papers:
- Adversaries With Incentives: A Strategic Alternative to Adversarial Robustness
Maayan Ehrenberg, Roy Ganz, Nir Rosenfeld
preprint - Classification Under Strategic Self-Selection
Guy Horowitz*, Yonatan Sommer*, Moran Koren, Nir Rosenfeld
ICML (2024) - One-Shot Strategic Classification Under Unknown Costs
Elan Rosenfeld, Nir Rosenfeld
ICML (2024) - Instructed to Bias: Instruction-Tuned Language Models Exhibit Emergent Cognitive Bias
Itay Itzhak , Gabriel Stanovsky, Nir Rosenfeld, Yonatan Belinkov
TACL (2024) - Decongestion by Representation: Learning to Improve Economic Welfare in Marketplaces
Omer Nahum, Gali Noti, David Parkes, Nir Rosenfeld
ICLR (2024) - Delegated Classification
Eden Saig, Inbal Talgam-Cohen, Nir Rosenfeld
NeurIPS (2023) - Causal Strategic Classification: A Tale of Two Shifts
Guy Horowitz, Nir Rosenfeld
ICML (2023) - Performative Recommendation: Diversifying Content via Strategic Incentives
Itay Eilat, Nir Rosenfeld
ICML (2023) - Learning to Take a Break: Sustainable Optimization of Long-Term User Engagement
Eden Saig, Nir Rosenfeld
ICML (2023) - Strategic Classification with Graph Neural Networks
Itay Eilat*, Ben Finkelshtein*, Chaim Baskin, Nir RosenfeldICLR (2023)
* equal contribution, alphabetical order - In the Eye of the Beholder: Robust Prediction with Causal User Modeling
Amir Feder, Guy Horowitz, Yoav Wald, Roi Reichart, Nir RosenfeldNeurIPS (2022)
- Generalized strategic classification and the case of aligned incentives
Sagi Levanon, Nir RosenfeldICML (2022)
- Strategic Representation
Vineet Nair, Ganesh Ghalme, Inbal Talgam-Cohen, Nir Rosenfeld
ICML (2022) - Strategic classification made practical
Sagi Levanon, Nir RosenfeldICML (2021)
- Strategic classification in the dark
Ganesh Ghalme*, Vineet Nair*, Itay Eilat, Inbal Talgam-Cohen, Nir RosenfeldICML (2021)
* equal contribution, alphabetical order - Learning representations by humans, for humans
Sophie Hilgard*, Nir Rosenfeld*, Mahzarin Banaji, Jack Cao, David ParkesICML (2021)
* equal contribution, alphabetical order - From predictions to decisions: Using lookahead regularization
Nir Rosenfeld, Sophie Hilgard, Sai Ravindranath, David ParkesNeurIPS (2020)
- Predicting choice with set-dependent aggregation
Nir Rosenfeld, Kojin Oshiba, Yaron SingerICML (2020)
- A kernel of truth: Determining rumor veracity on twitter by diffusion pattern alone
Nir Rosenfeld*, Aron Szanto*, David ParkesThe Web Conference (2020)
* equal contribution, alphabetical order - Learning to optimize combinatorial functions
Nir Rosenfeld, Eric Balkanski, Amir Globerson, Yaron SingerICML (2018)
- Discriminative learning of prediction intervals
Nir Rosenfeld, Yishay Mansour, Elad Yom-TovAISTATS (2018)
- Semi-supervised learning with competitive infection models
Nir Rosenfeld, Amir GlobersonAISTATS (2018)
- We look like our names: The manifestation of name stereotypes in facial appearance.
Yonat Zwebner, Anne-Laure Sellier, Nir Rosenfeld, Jacob Goldenberg, Ruth MayoJournal of Personality and Social Psychology (2017)
- Predicting counterfactuals from large historical data and small randomized trials
Nir Rosenfeld, Yishay Mansour, Elad Yom-TovThe Web Conference (2017)
- Discriminative learning of infection models
Nir Rosenfeld, Mor Nitzan, Amir GlobersonWSDM (2016)
- Optimal tagging with Markov chain optimization
Nir Rosenfeld, Amir GlobersonNeurIPS (2016)
- Learning Structured Models with the AUC Loss and Its Generalizations
Nir Rosenfeld, Ofer Meshi, Danny Tarlow, Amir GlobersonAISTATS (2014)
* equal contribution, alphabetical order within