Faculty of Computer Science · Technion — Israel Institute of Technology
Led by Prof. Nir Rosenfeld

Website · Publications · People · Google Scholar

Predictive models are deployed among people who have their own goals — applicants, sellers, users, agents. When they adapt to a model, the model changes the world it learned from.

We build the theory and tools for learning in these settings:

• Strategic classification — classifiers that account for strategic behavior
• Performative prediction — predictions that shape the outcomes they forecast
• Welfare-centric ML — learning objectives that reflect the welfare of the people models serve
• Aligned language models — LMs whose incentives align with their users

Lab members in bold. * equal contribution.

• Welfare-Optimal Classification with Accuracy Auctions — Bana Sadi*, Eden Saig*, Nir Rosenfeld. ICML 2026 · Spotlight. arXiv · Code
• Ambiguous Strategic Classification — Ivri Hikri, Nir Rosenfeld. ICML 2026. arXiv · Code
• The Role of Causal Features in Strategic Classification for Robustness and Alignment — Sophia Günlük, António Góis, Nir Rosenfeld, Nidhi Hegde, Simon Lacoste-Julien, Dhanya Sridhar. AISTATS 2026. arXiv
• Strategic PAC Learnability via Geometric Definability — Yuval Filmus, Shay Moran, Elizaveta Nesterova, Nir Rosenfeld, Alexander Shlimovich. Preprint. arXiv
• Welfare as a Guiding Principle for Machine Learning — From Compass, to Lens, to Roadmap — Nir Rosenfeld, Haifeng Xu. Preprint. arXiv

• Strategic Classification with Non-Linear Classifiers — Benyamin Trachtenberg, Nir Rosenfeld. NeurIPS 2025. arXiv · Code
• Evolutionary Prediction Games — Eden Saig, Nir Rosenfeld. NeurIPS 2025. arXiv · Code
• A Market for Accuracy: Classification Under Competition — Ohad Einav, Nir Rosenfeld. ICML 2025. arXiv · Code
• Learning Classifiers That Induce Markets — Yonatan Sommer, Ivri Hikri, Lotan Amit, Nir Rosenfeld. ICML 2025. arXiv · Code
• Adversaries With Incentives: A Strategic Alternative to Adversarial Robustness — Maayan Ehrenberg, Roy Ganz, Nir Rosenfeld. ICLR 2025. arXiv · Code

• Classification Under Strategic Self-Selection — Guy Horowitz*, Yonatan Sommer*, Moran Koren, Nir Rosenfeld. ICML 2024. arXiv · Code
• One-Shot Strategic Classification Under Unknown Costs — Elan Rosenfeld, Nir Rosenfeld. ICML 2024. arXiv
• Instructed to Bias: Instruction-Tuned Language Models Exhibit Emergent Cognitive Bias — Itay Itzhak, Gabriel Stanovsky, Nir Rosenfeld, Yonatan Belinkov. TACL 2024. arXiv · Code
• Decongestion by Representation: Learning to Improve Economic Welfare in Marketplaces — Omer Nahum, Gali Noti, David Parkes, Nir Rosenfeld. ICLR 2024. arXiv · Code

• Delegated Classification — Eden Saig, Inbal Talgam-Cohen, Nir Rosenfeld. NeurIPS 2023 · Spotlight. arXiv · Code
• Causal Strategic Classification: A Tale of Two Shifts — Guy Horowitz, Nir Rosenfeld. ICML 2023. arXiv · Code
• Performative Recommendation: Diversifying Content via Strategic Incentives — Itay Eilat, Nir Rosenfeld. ICML 2023. arXiv · Code
• Learning to Suggest Breaks: Sustainable Optimization of Long-Term User Engagement — Eden Saig, Nir Rosenfeld. ICML 2023. arXiv · Code
• Strategic Classification with Graph Neural Networks — Itay Eilat*, Ben Finkelshtein*, Chaim Baskin, Nir Rosenfeld. ICLR 2023. arXiv · Code

• In the Eye of the Beholder: Robust Prediction with Causal User Modeling — Amir Feder, Guy Horowitz, Yoav Wald, Roi Reichart, Nir Rosenfeld. NeurIPS 2022. arXiv
• Generalized Strategic Classification and the Case of Aligned Incentives — Sagi Levanon, Nir Rosenfeld. ICML 2022 · Long oral. arXiv · Code
• Strategic Representation — Vineet Nair, Ganesh Ghalme, Inbal Talgam-Cohen, Nir Rosenfeld. ICML 2022. arXiv

• Strategic Classification Made Practical — Sagi Levanon, Nir Rosenfeld. ICML 2021. arXiv · Code
• Strategic Classification in the Dark — Ganesh Ghalme*, Vineet Nair*, Itay Eilat, Inbal Talgam-Cohen, Nir Rosenfeld. ICML 2021 · Long oral. arXiv · Code

Earlier work and full list on Nir's page.

Prof. Nir Rosenfeld · nirr@cs.technion.ac.il

Behavioral Machine Learning Lab, Faculty of Computer Science, Technion, Haifa 3200003, Israel