no code implementations • 23 Feb 2024 • Guy Horowitz, Yonatan Sommer, Moran Koren, Nir Rosenfeld
When users stand to gain from certain predictions, they are prone to act strategically to obtain favorable predictive outcomes.
no code implementations • 5 Nov 2023 • Elan Rosenfeld, Nir Rosenfeld
The goal of strategic classification is to learn decision rules which are robust to strategic input manipulation.
1 code implementation • 1 Aug 2023 • Itay Itzhak, Gabriel Stanovsky, Nir Rosenfeld, Yonatan Belinkov
Recent studies show that instruction tuning (IT) and reinforcement learning from human feedback (RLHF) improve the abilities of large language models (LMs) dramatically.
1 code implementation • NeurIPS 2023 • Eden Saig, Inbal Talgam-Cohen, Nir Rosenfeld
When machine learning is outsourced to a rational agent, conflicts of interest might arise and severely impact predictive performance.
1 code implementation • 18 Jun 2023 • Omer Nahum, Gali Noti, David Parkes, Nir Rosenfeld
The power of a platform is limited to controlling representations -- the subset of information about items presented by default to users.
2 code implementations • 13 Feb 2023 • Guy Horowitz, Nir Rosenfeld
When users can benefit from certain predictive outcomes, they may be prone to act to achieve those outcome, e. g., by strategically modifying their features.
2 code implementations • 8 Feb 2023 • Itay Eilat, Nir Rosenfeld
The primary goal in recommendation is to suggest relevant content to users, but optimizing for accuracy often results in recommendations that lack diversity.
2 code implementations • 24 Nov 2022 • Eden Saig, Nir Rosenfeld
Optimizing user engagement is a key goal for modern recommendation systems, but blindly pushing users towards increased consumption risks burn-out, churn, or even addictive habits.
no code implementations • 17 Jun 2022 • Vineet Nair, Ganesh Ghalme, Inbal Talgam-Cohen, Nir Rosenfeld
In our main setting of interest, the system represents attributes of an item to the user, who then decides whether or not to consume.
no code implementations • 1 Jun 2022 • Amir Feder, Guy Horowitz, Yoav Wald, Roi Reichart, Nir Rosenfeld
Accurately predicting the relevance of items to users is crucial to the success of many social platforms.
1 code implementation • 31 May 2022 • Itay Eilat, Ben Finkelshtein, Chaim Baskin, Nir Rosenfeld
Strategic classification studies learning in settings where users can modify their features to obtain favorable predictions.
1 code implementation • 9 Feb 2022 • Sagi Levanon, Nir Rosenfeld
Our generalized model subsumes most current models but includes other novel settings; among these, we identify and target one intriguing sub-class of problems in which the interests of users and the system are aligned.
1 code implementation • 2 Mar 2021 • Sagi Levanon, Nir Rosenfeld
Our approach directly minimizes the "strategic" empirical risk, achieved by differentiating through the strategic response of users.
1 code implementation • 23 Feb 2021 • Ganesh Ghalme, Vineet Nair, Itay Eilat, Inbal Talgam-Cohen, Nir Rosenfeld
Strategic classification studies the interaction between a classification rule and the strategic agents it governs.
no code implementations • NeurIPS 2020 • Nir Rosenfeld, Sophie Hilgard, Sai Srivatsa Ravindranath, David C. Parkes
Machine learning is a powerful tool for predicting human-related outcomes, from credit scores to heart attack risks.
no code implementations • 28 Jan 2020 • Nir Rosenfeld, Aron Szanto, David C. Parkes
Recent work in the domain of misinformation detection has leveraged rich signals in the text and user identities associated with content on social media.
no code implementations • ICML 2020 • Nir Rosenfeld, Kojin Oshiba, Yaron Singer
Providing users with alternatives to choose from is an essential component in many online platforms, making the accurate prediction of choice vital to their success.
no code implementations • 29 May 2019 • Sophie Hilgard, Nir Rosenfeld, Mahzarin R. Banaji, Jack Cao, David C. Parkes
When machine predictors can achieve higher performance than the human decision-makers they support, improving the performance of human decision-makers is often conflated with improving machine accuracy.
no code implementations • ICLR 2019 • Kojin Oshiba, Nir Rosenfeld, Amir Globerson
Graph networks have recently attracted considerable interest, and in particular in the context of semi-supervised learning.
no code implementations • ICML 2018 • Nir Rosenfeld, Eric Balkanski, Amir Globerson, Yaron Singer
Submodular functions have become a ubiquitous tool in machine learning.
no code implementations • 16 Oct 2017 • Nir Rosenfeld, Yishay Mansour, Elad Yom-Tov
Most current methods for constructing prediction intervals offer guarantees for a single new test point.
no code implementations • 19 Mar 2017 • Nir Rosenfeld, Amir Globerson
The goal in semi-supervised learning is to effectively combine labeled and unlabeled data.
no code implementations • 24 Oct 2016 • Nir Rosenfeld, Yishay Mansour, Elad Yom-Tov
The conventional way to answer this counterfactual question is to estimate the effect of the new treatment in comparison to that of the conventional treatment by running a controlled, randomized experiment.