Author name cluster

Yoad Lewenberg

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

14 papers

2 author rows

AAAI Conference 2019 Conference Paper

“Reverse Gerrymandering”: Manipulation in Multi-Group Decision Making

Omer Lev
Yoad Lewenberg

District-based manipulation, or gerrymandering, is usually taken to refer to agents who are in fixed location, and an external division is imposed upon them. However, in many real-world setting, there is an external, fixed division – an organizational chart of a company, or markets for a particular product. In these cases, agents may wish to move around (“reverse gerrymandering”), as each of them tries to maximize their influence across the company’s subunits, or resources are “working” to be allocated to areas where they will be most needed. In this paper we explore an iterative dynamic in this setting, finding that allowing this decentralized system results, in some particular cases, in a stable equilibrium, though in general, the setting may end up in a cycle. We further examine how this decentralized process affects the social welfare of the system.

PDF Details

AAMAS Conference 2018 Conference Paper

Gerrymandering Over Graphs

Amittai Cohen-Zemach
Yoad Lewenberg
Jeffrey S. Rosenschein

In many real-life scenarios, voting problems consist of several phases: an overall set of voters is partitioned into subgroups, each subgroup chooses a preferred candidate, and the final winner is selected from among those candidates. The attempt to skew the outcome of such a voting system through strategic partitioning of the overall set of voters into subgroups is known as “gerrymandering”. We investigate the problem of gerrymandering over a network structure; the voters are embedded in a social network, and the task is to divide the network into connected components such that a target candidate will win in a plurality of the components. We first show that the problem is NP-complete in the worst case. We then perform a series of simulations, using random graph models incorporating a homophily factor. In these simulations, we show that a simple greedy algorithm can be quite successful in finding a partition in favor of a specific candidate.

PDF

IS Journal 2017 Journal Article

Agent Failures in All-Pay Auctions

Yoad Lewenberg
Omer Lev
Yoram Bachrach
Jeffrey S. Rosenschein

All-pay auctions, a common mechanism for various human and agent interactions, suffers (like many other mechanisms) from the possibility of players' failure to participate in the auction. The authors model such failures and fully characterize equilibrium for this class of games, presenting a symmetric equilibrium and showing that under some conditions the equilibrium is unique. They also reveal various properties of the equilibrium, such as the lack of influence of the most-likely-to-participate player on the behavior of the other players. The authors perform this analysis with two scenarios: the sum-profit model, in which the auctioneer obtains the sum of all submitted bids, and the max-profit model of crowdsourcing contests, in which the auctioneer can only use the best submissions and thus obtains only the winning bid. Finally, the authors examine various methods of influencing the probability of participation such as the effects of misreporting one's own probability of participating and how influencing another player's participation chances changes a player's strategy.

Details DOI

AAMAS Conference 2017 Conference Paper

Divide and Conquer: Using Geographic Manipulation to Win District-Based Elections

Yoad Lewenberg
Omer Lev
Jeffrey S. Rosenschein

District-based elections, in which voters vote for a district representative and those representatives ultimately choose the winner, are vulnerable to gerrymandering, i. e. , manipulation of the outcome by changing the location and borders of districts. Many countries aim to limit blatant gerrymandering, and thus we introduce a geographically-based manipulation problem, where voters must vote at the ballot box closest to them. We show that this problem is NP-complete in the worst case. However, we present a greedy algorithm for the problem; testing it both on simulation data as well as on realworld data from the 2015 Israeli and British elections, we show that many parties are potentially able to make themselves victorious using district manipulation. Moreover, we show that the relevant variables here go beyond share of the vote; the form of geographic dispersion also plays a crucial role. CCS Concepts •Theory of computation → Solution concepts in game theory; •Applied computing → Sociology;

PDF

AAAI Conference 2017 Conference Paper

Knowing What to Ask: A Bayesian Active Learning Approach to the Surveying Problem

Yoad Lewenberg
Yoram Bachrach
Ulrich Paquet
Jeffrey Rosenschein

We examine the surveying problem, where we attempt to predict how a target user is likely to respond to questions by iteratively querying that user, collaboratively based on the responses of a sample set of users. We focus on an active learning approach, where the next question we select to ask the user depends on their responses to the previous questions. We propose a method for solving the problem based on a Bayesian dimensionality reduction technique. We empirically evaluate our method, contrasting it to benchmark approaches based on augmented linear regression, and show that it achieves much better predictive performance, and is much more robust when there is missing data.

PDF Details

IJCAI Conference 2017 Conference Paper

Machine Learning Techniques for MultiAgent Systems

Yoad Lewenberg

Research in artificial intelligence ranges over many subdisciplines, such as Natural Language Processing, Computer Vision, Machine Learning, and MultiAgent Systems. Recently, AI techniques have become increasingly robust and complex, and there has been enhanced interest in research at the intersection of seemingly disparate research areas. Such work is motivated by the observation that there is actually a great deal of commonality among areas, that can be exploited within subfields. One example of a successful combination is the intersection of machine learning and multiagent systems. For example, Kearns et al. [2001] proposed an efficient graphical model-based algorithm for calculating Nash equilibria. Going in the other direction, Datta et al. [2015] showed that solution concepts from cooperative game theory can be used to uniquely characterize the influence measure of classifiers.

PDF Details

IJCAI Conference 2016 Conference Paper

Misrepresentation in District Voting

Yoram Bachrach
Omer Lev
Yoad Lewenberg
Yair Zick

Voting systems in which voters are partitioned to districts encourage accountability by providing voters an easily identifiable district representative, but can result in a selection of representatives not representative of the electorate's preferences. In some cases, a party may have a majority of the popular vote, but lose the elections due to districting effects. We define the Misrepresentation Ratio which quantifies the deviation from proportional representation in a district-based election, and provide bounds for this ratio under various voting rules. We also examine probabilistic models for election outcomes, and provide an algorithm for approximating the expected Misrepresentation Ratio under a given probabilistic election model. Finally, we provide simulation results for several such probabilistic election models, showing the effects of the number of voters and candidates on the misrepresentation ratio.

PDF Details

UAI Conference 2016 Conference Paper

Political Dimensionality Estimation Using a Probabilistic Graphical Model

Yoad Lewenberg
Yoram Bachrach
Lucas Bordeaux
Pushmeet Kohli

This paper attempts to move beyond the left-right characterization of political ideologies. We propose a trait based probabilistic model for estimating the manifold of political opinion. We demonstrate the efficacy of our model on two novel and large scale datasets of public opinion. Our experiments show that although the political spectrum is richer than a simple left-right structure, peoples’ opinions on seemingly unrelated political issues are very correlated, so fewer than 10 dimensions are enough to represent peoples’ entire political opinion.

Details

AAAI Conference 2016 Conference Paper

Predicting Gaming Related Properties from Twitter Accounts

Maria Gorinova
Yoad Lewenberg
Yoram Bachrach
Alfredo Kalaitzis
Michael Fagan
Dean Carignan
Nitin Gautam

We demonstrate a system for predicting gaming related properties from Twitter accounts. Our system predicts various traits of users based on the tweets publicly available in their proﬁles. Such inferred traits include degrees of tech-savviness and knowledge on computer games, actual gaming performance, preferred platform, degree of originality, humor and inﬂuence on others. Our system is based on machine learning models trained on crowd-sourced data. It allows people to select Twitter accounts of their fellow gamers, examine the trait predictions made by our system, and the main drivers of these predictions. We present empirical results on the performance of our system based on its accuracy on our crowd-sourced dataset.

PDF Details

IJCAI Conference 2016 Conference Paper

Predicting Personal Traits from Facial Images Using Convolutional Neural Networks Augmented with Facial Landmark Information

Yoad Lewenberg
Yoram Bachrach
Sukrit Shankar
Antonio Criminisi

We consider the task of predicting various traits of a person given an image of their face. We estimate both objective traits, such as gender, ethnicity and hair-color; as well as subjective traits, such as the emotion a person expresses or whether he is humorous or attractive. For sizeable experimentation, we contribute a new Face Attributes Dataset (FAD), having roughly 200, 000 attribute labels for the above traits, for over 10, 000 facial images. Due to the recent surge of research on Deep Convolutional Neural Networks (CNNs), we begin by using a CNN architecture for estimating facial attributes and show that they indeed provide an impressive baseline performance. To further improve performance, we propose a novel approach that incorporates facial landmark information for input images as an additional channel, helping the CNN learn better attribute-specific features so that the landmarks across various training images hold correspondence. We empirically analyse the performance of our method, showing consistent improvement over the baseline across traits.

PDF Details

AAAI Conference 2016 Conference Paper

Predicting Personal Traits from Facial Images Using Convolutional Neural Networks Augmented with Facial Landmark Information

Yoad Lewenberg
Yoram Bachrach
Sukrit Shankar
Antonio Criminisi

We consider the task of predicting various traits of a person given an image of their face. We aim to estimate traits such as gender, ethnicity and age, as well as more subjective traits as the emotion a person expresses or whether they are humorous or attractive. Due to the recent surge of research on Deep Convolutional Neural Networks (CNNs), we begin by using a CNN architecture, and corroborate that CNNs are promising for facial attribute prediction. To further improve performance, we propose a novel approach that incorporates facial landmark information for input images as an additional channel, helping the CNN learn face-speciﬁc features so that the landmarks across various training images hold correspondence. We empirically analyze the performance of our proposed method, showing consistent improvement over the baselines across traits. We demonstrate our system on a sizeable Face Attributes Dataset (FAD), comprising of roughly 200, 000 labels, for 10 most sought-after traits, for over 10, 000 facial images.

PDF Details

AAMAS Conference 2016 Conference Paper

Tracking Performance and Forming Study Groups for Prep Courses Using Probabilistic Graphical Models (Extended Abstract)

Yoram Bachrach
Yoad Lewenberg
Jeffrey S. Rosenschein
Yair Zick

Efficient tracking of class performance across topics is an important aspect of classroom teaching; this is especially true for psychometric general intelligence exams, which test a varied range of abilities. We develop a framework that uncovers a hidden thematic structure underlying student responses to a large pool of questions, using a probabilistic graphical model. General Terms Experimentation, Theory

PDF

AAAI Conference 2016 Conference Paper

Using Convolutional Neural Networks to Analyze Function Properties from Images

Yoad Lewenberg
Yoram Bachrach
Ian Kash
Peter Key

We propose a system for determining properties of mathematical functions given an image of their graph representation. We demonstrate our approach for twodimensional graphs (curves of single variable functions) and three-dimensional graphs (surfaces of two variable functions), studying the properties of convexity and symmetry. Our method uses a Convolutional Neural Network which classiﬁes functions according to these properties, without using any hand-crafted features. We propose algorithms for randomly constructing functions with convexity or symmetry properties, and use the images generated by these algorithms to train our network. Our system achieves a high accuracy on this task, even for functions where humans ﬁnd it difﬁcult to determine the function’s properties from its image.

PDF Details

IJCAI Conference 2013 Conference Paper

Agent Failures in All-Pay Auctions

Yoad Lewenberg
Omer Lev
Yoram Bachrach
Jeffrey S. Rosenschein

All-pay auctions, a common mechanism for various human and agent interactions, suffers, like many other mechanisms, from the possibility of players’ failure to participate in the auction. We model such failures and show how they affect the equilibrium state, revealing various properties, such as the lack of influence of the most-likely-to-participate player on the behavior of the other players. We perform this analysis with two scenarios: the sum-profit model, where the auctioneer obtains the sum of all submitted bids, and the max-profit model of crowdsourcing contests, where the auctioneer can only use the best submissions and thus obtains only the winning bid. Furthermore, we examine various methods of influencing the probability of participation such as the effects of misreporting one’s own probability of participating, and how influencing another player’s participation chances (e. g. , sabotage) changes the player’s strategy.

PDF Details DOI