no code implementations • 19 May 2024 • Omer Madmon, Idan Pipano, Itamar Reinman, Moshe Tennenholtz
Publishers who publish their content on the web act strategically, in a behavior that can be modeled within the online learning framework.
no code implementations • 14 Apr 2024 • Haya Nachimovsky, Moshe Tennenholtz, Fiana Raiber, Oren Kurland
Previous work on the competitive retrieval setting focused on a single-query setting: document authors manipulate their documents so as to improve their future ranking for a given query.
no code implementations • 26 Mar 2024 • Yotam Gafni, Ronen Gradwohl, Moshe Tennenholtz
Second, we narrow our focus to two natural settings within this framework: (i) a setting in which the accuracy of each firm's prediction model is common knowledge, but the correlation between the respective models is unknown; and (ii) a setting in which two hypotheses exist regarding the optimal predictor, and one of the firms has a structural advantage in deducing it.
no code implementations • 14 Feb 2024 • Narun Raman, Taylor Lundy, Samuel Amouyal, Yoav Levine, Kevin Leyton-Brown, Moshe Tennenholtz
We begin by surveying the economic literature on rational decision making, taxonomizing a large set of fine-grained "elements" that an agent should exhibit, along with dependencies between them.
no code implementations • 30 Jan 2024 • Itai Arieli, Yakov Babichenko, Omer Madmon, Moshe Tennenholtz
We consider a model of third-degree price discrimination, in which the seller has a valuation for the product which is unknown to the market designer, who aims to maximize the buyers' surplus by revealing information regarding the buyer's valuation to the seller.
no code implementations • 30 Jan 2024 • Eilam Shapira, Omer Madmon, Roi Reichart, Moshe Tennenholtz
Economic choice prediction is an essential challenging task, often constrained by the difficulties in acquiring human choice data.
no code implementations • 11 Jul 2023 • Itai Arieli, Ivan Geffner, Moshe Tennenholtz
The payoff of the senders and of the receiver depend on both the state of the world and the action selected by the receiver.
no code implementations • 26 May 2023 • Omer Madmon, Idan Pipano, Itamar Reinman, Moshe Tennenholtz
We study a game-theoretic information retrieval model in which strategic publishers aim to maximize their chances of being ranked first by the search engine while maintaining the integrity of their original documents.
1 code implementation • 17 May 2023 • Eilam Shapira, Reut Apel, Moshe Tennenholtz, Roi Reichart
Recent advances in Large Language Models (LLMs) have spurred interest in designing LLM-based agents for tasks that involve interaction with human and artificial agents.
no code implementations • 27 Oct 2022 • Yotam Gafni, Moshe Tennenholtz
We consider two refined notions: (i) a term we call DSL (distinguishable safety level), and is based on the notion of ``discrimin'', which uses a pairwise comparison of actions while removing trivial equivalencies.
no code implementations • 27 Mar 2022 • Amir Ban, Moshe Tennenholtz
Commercial entries, such as hotels, are ranked according to score by a search engine or recommendation system, and the score of each can be improved upon by making a targeted investment, e. g., advertising.
1 code implementation • 22 Jan 2022 • Yotam Gafni, Moshe Tennenholtz
We conclude that the choice of protocol, as well as the number of Sybil identities an attacker may control, is material to vulnerability.
1 code implementation • 21 Oct 2021 • Gregory Goren, Oren Kurland, Moshe Tennenholtz, Fiana Raiber
We present a first study of the ability of search engines to drive pre-defined, targeted, content effects in the corpus using simple techniques.
no code implementations • 11 May 2021 • Maya Raifer, Guy Rotman, Reut Apel, Moshe Tennenholtz, Roi Reichart
Persuasion games are fundamental in economics and AI research and serve as the basis for important applications.
1 code implementation • 17 Dec 2020 • Reut Apel, Ido Erev, Roi Reichart, Moshe Tennenholtz
Our results demonstrate that given a prefix of the interaction sequence, our models can predict the future decisions of the decision-maker, particularly when a sequential modeling approach and hand-crafted textual features are applied.
no code implementations • NeurIPS 2020 • Omer Ben-Porat, Itay Rosenberg, Moshe Tennenholtz
Recommendation Systems like YouTube are vibrant ecosystems with two types of users: Content consumers (those who watch videos) and content providers (those who create videos).
1 code implementation • ICLR 2021 • Yoav Levine, Barak Lenz, Opher Lieber, Omri Abend, Kevin Leyton-Brown, Moshe Tennenholtz, Yoav Shoham
Specifically, we show experimentally that PMI-Masking reaches the performance of prior masking approaches in half the training time, and consistently improves performance at the end of training.
no code implementations • 14 Jun 2020 • Reshef Meir, Fedor Sandomirskiy, Moshe Tennenholtz
We show that a k-sortition (a random committee of k voters with the majority vote within the committee) leads to an outcome within the factor 1+O(1/k) of the optimal social cost for any number of voters n, any number of issues $m$, and any preference profile.
no code implementations • 8 Jun 2020 • Gal Bahar, Omer Ben-Porat, Kevin Leyton-Brown, Moshe Tennenholtz
A recent body of work addresses safety constraints in explore-and-exploit systems.
no code implementations • 28 May 2020 • Ziv Vasilisky, Moshe Tennenholtz, Oren Kurland
The ranking incentives of many authors of Web pages play an important role in the Web dynamics.
2 code implementations • 26 May 2020 • Gregory Goren, Oren Kurland, Moshe Tennenholtz, Fiana Raiber
The Web is a canonical example of a competitive retrieval setting where many documents' authors consistently modify their documents to promote them in rankings.
1 code implementation • 6 Apr 2020 • Omer Ben-Porat, Sharon Hirsch, Lital Kuchy, Guy Elad, Roi Reichart, Moshe Tennenholtz
In ablation analysis, we demonstrate the importance of our modeling choices---the representation of the text with the commonsensical personality attributes and our classifier---to the predictive power of our model.
no code implementations • 20 Jun 2019 • Gilie Gefen, Omer Ben-Porat, Moshe Tennenholtz, Elad Yom-Tov
Here we describe experiments where methods from Mechanism Design were used to elicit a truthful valuation from users for their Internet data and for services to screen people for medical conditions.
no code implementations • 25 May 2019 • Omer Ben-Porat, Fedor Sandomirskiy, Moshe Tennenholtz
In this family, we characterize conditions under which the fairness constraint helps the disadvantaged group.
no code implementations • ICML 2020 • Gal Bahar, Omer Ben-Porat, Kevin Leyton-Brown, Moshe Tennenholtz
Recommendation systems often face exploration-exploitation tradeoffs: the system can only learn about the desirability of new options by recommending them to some user.
1 code implementation • 4 May 2019 • Omer Ben-Porat, Moshe Tennenholtz
Despite their centrality in the competition between online companies who offer prediction-based products, the \textit{strategic} use of prediction algorithms remains unexplored.
no code implementations • 15 Apr 2019 • Ori Plonsky, Reut Apel, Eyal Ert, Moshe Tennenholtz, David Bourgin, Joshua C. Peterson, Daniel Reichman, Thomas L. Griffiths, Stuart J. Russell, Evan C. Carter, James F. Cavanagh, Ido Erev
Here, we introduce BEAST Gradient Boosting (BEAST-GB), a novel hybrid model that synergizes behavioral theories, specifically the model BEAST, with machine learning techniques.
no code implementations • 14 Jun 2018 • Omer Ben-Porat, Itay Rosenberg, Moshe Tennenholtz
We consider a game-theoretic model of information retrieval with strategic authors.
no code implementations • 5 Jun 2018 • Omer Ben-Porat, Moshe Tennenholtz
Despite their centrality in the competition between online companies who offer prediction-based products, the strategic use of prediction algorithms remains unexplored.
Computer Science and Game Theory
1 code implementation • 1 May 2018 • Reut Apel, Elad Yom-Tov, Moshe Tennenholtz
Users of social networks often focus on specific areas of that network, leading to the well-known "filter bubble" effect.
Social and Information Networks
1 code implementation • NeurIPS 2017 • Omer Ben-Porat, Moshe Tennenholtz
In this work, we initiate the study of strategic predictions in machine learning.
no code implementations • 27 Jul 2017 • Omer Lev, Moshe Tennenholtz
We introduce an axiomatic approach to group recommendations, in line of previous work on the axiomatic treatment of trust-based recommendation systems, ranking systems, and other foundational work on the axiomatic approach to internet mechanisms in social choice settings.
no code implementations • 24 Jun 2016 • Omer Lev, Moshe Tennenholtz, Aviv Zohar
Information delivery in a network of agents is a key issue for large, complex systems that need to do so in a predictable, efficient manner.
no code implementations • 13 May 2016 • Irit Hochberg, Guy Feraru, Mark Kozdoba, Shie Mannor, Moshe Tennenholtz, Elad Yom-Tov
Messages were personalized through a Reinforcement Learning (RL) algorithm which optimized messages to improve each participant's compliance with the activity regimen.
no code implementations • 29 Jul 2014 • Uriel Feige, Tomer Koren, Moshe Tennenholtz
We consider sequential decision making in a setting where regret is measured with respect to a set of stateful reference policies, and feedback is limited to observing the rewards of the actions performed (the so called "bandit" setting).