arXiv subjects

Lirong Xia

Publications and source records attributed to Lirong Xia.

At least 73 records · Page 4Linked to original sources

arXiv2020

Fair Division through Information Withholding

Envy-freeness up to one good (EF1) is a well-studied fairness notion for indivisible goods that addresses pairwise envy by the removal of at most one good. In the worst case, each pair of agents might require the (hypothetical) removal of a different good, resulting in a weak aggregate guarantee. We study allocations that are nearly envy-free in aggregate, and define a novel fairness notion based on information withholding. Under this notion, an agent can withhold (or hide) some of the goods in its bundle and reveal the remaining goods to the other agents. We observe that in practice, envy-freeness can be achieved by withholding only a small number of goods overall. We show that finding allocations that withhold an optimal number of goods is computationally hard even for highly restricted classes of valuations. In contrast to the worst-case results, our experiments on synthetic and real-world preference data show that existing algorithms for finding EF1 allocations withhold close-to-optimal number of goods.

cs.GT↗

arXiv2020

Learning Mixtures of Plackett-Luce Models

In this paper we address the identifiability and efficient learning problems of finite mixtures of Plackett-Luce models for rank data. We prove that for any $k\geq 2$, the mixture of $k$ Plackett-Luce models for no more than $2k-1$ alternatives is non-identifiable and this bound is tight for $k=2$. For generic identifiability, we prove that the mixture of $k$ Plackett-Luce models over $m$ alternatives is generically identifiable if $k\leq\lfloor\frac {m-2} 2\rfloor!$. We also propose an efficient generalized method of moments (GMM) algorithm to learn the mixture of two Plackett-Luce models and show that the algorithm is consistent. Our experiments show that our GMM algorithm is significantly faster than the EMM algorithm by Gormley and Murphy (2008), while achieving competitive statistical efficiency.

cs.LG↗

arXiv2020

Equitable Allocations of Indivisible Chores

We study fair allocation of indivisible chores (i.e., items with non-positive value) among agents with additive valuations. An allocation is deemed fair if it is (approximately) equitable, which means that the disutilities of the agents are (approximately) equal. Our main theoretical contribution is to show that there always exists an allocation that is simultaneously equitable up to one chore (EQ1) and Pareto optimal (PO), and to provide a pseudopolynomial-time algorithm for computing such an allocation. In addition, we observe that the Leximin solution---which is known to satisfy a strong form of approximate equitability in the goods setting---fails to satisfy even EQ1 for chores. It does, however, satisfy a novel fairness notion that we call equitability up to any duplicated chore. Our experiments on synthetic as well as real-world data obtained from the Spliddit website reveal that the algorithms considered in our work satisfy approximate fairness and efficiency properties significantly more often than the algorithm currently deployed on Spliddit.

cs.GT↗

arXiv2019

Learning Mixtures of Plackett-Luce Models from Structured Partial Orders

Mixtures of ranking models have been widely used for heterogeneous preferences. However, learning a mixture model is highly nontrivial, especially when the dataset consists of partial orders. In such cases, the parameter of the model may not be even identifiable. In this paper, we focus on three popular structures of partial orders: ranked top-$l_1$, $l_2$-way, and choice data over a subset of alternatives. We prove that when the dataset consists of combinations of ranked top-$l_1$ and $l_2$-way (or choice data over up to $l_2$ alternatives), mixture of $k$ Plackett-Luce models is not identifiable when $l_1+l_2\le 2k-1$ ($l_2$ is set to $1$ when there are no $l_2$-way orders). We also prove that under some combinations, including ranked top-$3$, ranked top-$2$ plus $2$-way, and choice data over up to $4$ alternatives, mixtures of two Plackett-Luce models are identifiable. Guided by our theoretical results, we propose efficient generalized method of moments (GMM) algorithms to learn mixtures of two Plackett-Luce models, which are proven consistent. Our experiments demonstrate the efficacy of our algorithms. Moreover, we show that when full rankings are available, learning from different marginal events (partial orders) provides tradeoffs between statistical efficiency and computational efficiency.

cs.LG↗

arXiv2019

Minimizing Time-to-Rank: A Learning and Recommendation Approach

Consider the following problem faced by an online voting platform: A user is provided with a list of alternatives, and is asked to rank them in order of preference using only drag-and-drop operations. The platform's goal is to recommend an initial ranking that minimizes the time spent by the user in arriving at her desired ranking. We develop the first optimization framework to address this problem, and make theoretical as well as practical contributions. On the practical side, our experiments on Amazon Mechanical Turk provide two interesting insights about user behavior: First, that users' ranking strategies closely resemble selection or insertion sort, and second, that the time taken for a drag-and-drop operation depends linearly on the number of positions moved. These insights directly motivate our theoretical model of the optimization problem. We show that computing an optimal recommendation is NP-hard, and provide exact and approximation algorithms for a variety of special cases of the problem. Experimental evaluation on MTurk shows that, compared to a random recommendation strategy, the proposed approach reduces the (average) time-to-rank by up to 50%.

cs.HC↗

arXiv2019

Equitable Allocations of Indivisible Goods

In fair division, equitability dictates that each participant receives the same level of utility. In this work, we study equitable allocations of indivisible goods among agents with additive valuations. While prior work has studied (approximate) equitability in isolation, we consider equitability in conjunction with other well-studied notions of fairness and economic efficiency. We show that the Leximin algorithm produces an allocation that satisfies equitability up to any good and Pareto optimality. We also give a novel algorithm that guarantees Pareto optimality and equitability up to one good in pseudopolynomial time. Our experiments on real-world preference data reveal that approximate envy-freeness, approximate equitability, and Pareto optimality can often be achieved simultaneously.

cs.GT↗

arXiv2019

Differential Privacy for Eye-Tracking Data

As large eye-tracking datasets are created, data privacy is a pressing concern for the eye-tracking community. De-identifying data does not guarantee privacy because multiple datasets can be linked for inferences. A common belief is that aggregating individuals' data into composite representations such as heatmaps protects the individual. However, we analytically examine the privacy of (noise-free) heatmaps and show that they do not guarantee privacy. We further propose two noise mechanisms that guarantee privacy and analyze their privacy-utility tradeoff. Analysis reveals that our Gaussian noise mechanism is an elegant solution to preserve privacy for heatmaps. Our results have implications for interdisciplinary research to create differentially private mechanisms for eye tracking.

cs.CR↗

arXiv2019

Practical Algorithms for Multi-Stage Voting Rules with Parallel Universes Tiebreaking

STV and ranked pairs (RP) are two well-studied voting rules for group decision-making. They proceed in multiple rounds, and are affected by how ties are broken in each round. However, the literature is surprisingly vague about how ties should be broken. We propose the first algorithms for computing the set of alternatives that are winners under some tiebreaking mechanism under STV and RP, which is also known as parallel-universes tiebreaking (PUT). Unfortunately, PUT-winners are NP-complete to compute under STV and RP, and standard search algorithms from AI do not apply. We propose multiple DFS-based algorithms along with pruning strategies, heuristics, sampling and machine learning to prioritize search direction to significantly improve the performance. We also propose novel ILP formulations for PUT-winners under STV and RP, respectively. Experiments on synthetic and real-world data show that our algorithms are overall faster than ILP.

cs.AI↗

arXiv2018

A Mathematical Model for Optimal Decisions in a Representative Democracy

Direct democracy is a special case of an ensemble of classifiers, where every person (classifier) votes on every issue. This fails when the average voter competence (classifier accuracy) falls below 50%, which can happen in noisy settings where voters have only limited information, or when there are multiple topics and the average voter competence may not be high enough for some topics. Representative democracy, where voters choose representatives to vote, can be an elixir in both these situations. Representative democracy is a specific way to improve the ensemble of classifiers. We introduce a mathematical model for studying representative democracy, in particular understanding the parameters of a representative democracy that gives maximum decision making capability. Our main result states that under general and natural conditions, 1. Representative democracy can make the correct decisions simultaneously for multiple noisy issues. 2. When the cost of voting is fixed, the optimal representative democracy requires that representatives are elected from constant sized groups: the number of representatives should be linear in the number of voters. 3. When the cost and benefit of voting are both polynomial, the optimal group size is close to linear in the number of voters. This work sets the mathematical foundation for studying the quality-quantity tradeoff in a representative democracy-type ensemble (fewer highly qualified representatives versus more less qualified representatives).

cs.GT↗

arXiv2018

Towards Non-Parametric Learning to Rank

This paper studies a stylized, yet natural, learning-to-rank problem and points out the critical incorrectness of a widely used nearest neighbor algorithm. We consider a model with $n$ agents (users) $\{x_i\}_{i \in [n]}$ and $m$ alternatives (items) $\{y_j\}_{j \in [m]}$, each of which is associated with a latent feature vector. Agents rank items nondeterministically according to the Plackett-Luce model, where the higher the utility of an item to the agent, the more likely this item will be ranked high by the agent. Our goal is to find neighbors of an arbitrary agent or alternative in the latent space. We first show that the Kendall-tau distance based kNN produces incorrect results in our model. Next, we fix the problem by introducing a new algorithm with features constructed from "global information" of the data matrix. Our approach is in sharp contrast to most existing feature engineering methods. Finally, we design another new algorithm identifying similar alternatives. The construction of alternative features can be done using "local information," highlighting the algorithmic difference between finding similar agents and similar alternatives.

cs.LG↗

arXiv2018

A Cost-Effective Framework for Preference Elicitation and Aggregation

We propose a cost-effective framework for preference elicitation and aggregation under the Plackett-Luce model with features. Given a budget, our framework iteratively computes the most cost-effective elicitation questions in order to help the agents make a better group decision. We illustrate the viability of the framework with experiments on Amazon Mechanical Turk, which we use to estimate the cost of answering different types of elicitation questions. We compare the prediction accuracy of our framework when adopting various information criteria that evaluate the expected information gain from a question. Our experiments show carefully designed information criteria are much more efficient, i.e., they arrive at the correct answer using fewer queries, than randomly asking questions given the budget constraint.

cs.LG↗

arXiv2018

Composite Marginal Likelihood Methods for Random Utility Models

We propose a novel and flexible rank-breaking-then-composite-marginal-likelihood (RBCML) framework for learning random utility models (RUMs), which include the Plackett-Luce model. We characterize conditions for the objective function of RBCML to be strictly log-concave by proving that strict log-concavity is preserved under convolution and marginalization. We characterize necessary and sufficient conditions for RBCML to satisfy consistency and asymptotic normality. Experiments on synthetic data show that RBCML for Gaussian RUMs achieves better statistical efficiency and computational efficiency than the state-of-the-art algorithm and our RBCML for the Plackett-Luce model provides flexible tradeoffs between running time and statistical efficiency.

cs.LG↗

arXiv2018

Practical Algorithms for STV and Ranked Pairs with Parallel Universes Tiebreaking

STV and ranked pairs (RP) are two well-studied voting rules for group decision-making. They proceed in multiple rounds, and are affected by how ties are broken in each round. However, the literature is surprisingly vague about how ties should be broken. We propose the first algorithms for computing the set of alternatives that are winners under some tiebreaking mechanism under STV and RP, which is also known as parallel-universes tiebreaking (PUT). Unfortunately, PUT-winners are NP-complete to compute under STV and RP, and standard search algorithms from AI do not apply. We propose multiple DFS-based algorithms along with pruning strategies and heuristics to prioritize search direction to significantly improve the performance using machine learning. We also propose novel ILP formulations for PUT-winners under STV and RP, respectively. Experiments on synthetic and real-world data show that our algorithms are overall significantly faster than ILP, while there are a few cases where ILP is significantly faster for RP.

cs.AI↗

arXiv2016

Mechanism Design for Multi-Type Housing Markets

We study multi-type housing markets, where there are $p\ge 2$ types of items, each agent is initially endowed one item of each type, and the goal is to design mechanisms without monetary transfer to (re)allocate items to the agents based on their preferences over bundles of items, such that each agent gets one item of each type. In sharp contrast to classical housing markets, previous studies in multi-type housing markets have been hindered by the lack of natural solution concepts, because the strict core might be empty. We break the barrier in the literature by leveraging AI techniques and making natural assumptions on agents' preferences. We show that when agents' preferences are lexicographic, even with different importance orders, the classical top-trading-cycles mechanism can be extended while preserving most of its nice properties. We also investigate computational complexity of checking whether an allocation is in the strict core and checking whether the strict core is empty. Our results convey an encouragingly positive message: it is possible to design good mechanisms for multi-type housing markets under natural assumptions on preferences.

cs.GT↗

arXiv2016

A Statistical Decision-Theoretic Framework for Social Choice

In this paper, we take a statistical decision-theoretic viewpoint on social choice, putting a focus on the decision to be made on behalf of a system of agents. In our framework, we are given a statistical ranking model, a decision space, and a loss function defined on (parameter, decision) pairs, and formulate social choice mechanisms as decision rules that minimize expected loss. This suggests a general framework for the design and analysis of new social choice mechanisms. We compare Bayesian estimators, which minimize Bayesian expected loss, for the Mallows model and the Condorcet model respectively, and the Kemeny rule. We consider various normative properties, in addition to computational complexity and asymptotic behavior. In particular, we show that the Bayesian estimator for the Condorcet model satisfies some desired properties such as anonymity, neutrality, and monotonicity, can be computed in polynomial time, and is asymptotically different from the other two rules when the data are generated from the Condorcet model for some ground truth parameter.

cs.AI↗

arXiv2015

Welfare of Sequential Allocation Mechanisms for Indivisible Goods

Sequential allocation is a simple and attractive mechanism for the allocation of indivisible goods. Agents take turns, according to a policy, to pick items. Sequential allocation is guaranteed to return an allocation which is efficient but may not have an optimal social welfare. We consider therefore the relation between welfare and efficiency. We study the (computational) questions of what welfare is possible or necessary depending on the choice of policy. We also consider a novel control problem in which the chair chooses a policy to improve social welfare.

cs.AI↗

arXiv2015

Allocating Indivisible Items in Categorized Domains

We formulate a general class of allocation problems called categorized domain allocation problems (CDAPs), where indivisible items from multiple categories are allocated to agents without monetary transfer and each agent gets at least one item per category. We focus on basic CDAPs, where the number of items in each category is equal to the number of agents. We characterize serial dictatorships for basic CDAPs by a minimal set of three axiomatic properties: strategy-proofness, non-bossiness, and category-wise neutrality. Then, we propose a natural extension of serial dictatorships called categorial sequential allocation mechanisms (CSAMs), which allocate the items in multiple rounds: in each round, the active agent chooses an item from a designated category. We fully characterize the worst-case rank efficiency of CSAMs for optimistic and pessimistic agents, and provide a bound for strategic agents. We also conduct experiments to compare expected rank efficiency of various CSAMs w.r.t. random generated data.

cs.GT↗

arXiv2014

Possible and Necessary Allocations via Sequential Mechanisms

A simple mechanism for allocating indivisible resources is sequential allocation in which agents take turns to pick items. We focus on possible and necessary allocation problems, checking whether allocations of a given form occur in some or all mechanisms for several commonly used classes of sequential allocation mechanisms. In particular, we consider whether a given agent receives a given item, a set of items, or a subset of items for five natural classes of sequential allocation mechanisms: balanced, recursively balanced, balanced alternating, strictly alternating and all policies. We identify characterizations of allocations produced balanced, recursively balanced, balanced alternating policies and strictly alternating policies respectively, which extend the well-known characterization by Brams and King [2005] for policies without restrictions. In addition, we examine the computational complexity of possible and necessary allocation problems for these classes.

cs.AI↗