arXiv subjects

Aleksandrs Slivkins

Publications and source records attributed to Aleksandrs Slivkins.

72 records · Page 4Linked to original sources

arXiv2015

Adaptive Contract Design for Crowdsourcing Markets: Bandit Algorithms for Repeated Principal-Agent Problems

Crowdsourcing markets have emerged as a popular platform for matching available workers with tasks to complete. The payment for a particular task is typically set by the task's requester, and may be adjusted based on the quality of the completed work, for example, through the use of "bonus" payments. In this paper, we study the requester's problem of dynamically adjusting quality-contingent payments for tasks. We consider a multi-round version of the well-known principal-agent model, whereby in each round a worker makes a strategic choice of the effort level which is not directly observable by the requester. In particular, our formulation significantly generalizes the budget-free online task pricing problems studied in prior work. We treat this problem as a multi-armed bandit problem, with each "arm" representing a potential contract. To cope with the large (and in fact, infinite) number of arms, we propose a new algorithm, AgnosticZooming, which discretizes the contract space into a finite number of regions, effectively treating each region as a single arm. This discretization is adaptively refined, so that more promising regions of the contract space are eventually discretized more finely. We analyze this algorithm, showing that it achieves regret sublinear in the time horizon and substantially improves over non-adaptive discretization (which is the only competing approach in the literature). Our results advance the state of art on several different topics: the theory of crowdsourcing markets, principal-agent problems, multi-armed bandits, and dynamic pricing.

cs.DS↗

arXiv2015

Resourceful Contextual Bandits

We study contextual bandits with ancillary constraints on resources, which are common in real-world applications such as choosing ads or dynamic pricing of items. We design the first algorithm for solving these problems that handles constrained resources other than time, and improves over a trivial reduction to the non-contextual case. We consider very general settings for both contextual bandits (arbitrary policy sets, e.g. Dudik et al. (UAI'11)) and bandits with resource constraints (bandits with knapsacks, Badanidiyuru et al. (FOCS'13)), and prove a regret guarantee with near-optimal statistical properties.

cs.LG↗

arXiv2015

Contextual Dueling Bandits

We consider the problem of learning to choose actions using contextual information when provided with limited feedback in the form of relative pairwise comparisons. We study this problem in the dueling-bandits framework of Yue et al. (2009), which we extend to incorporate context. Roughly, the learner's goal is to find the best policy, or way of behaving, in some space of policies, although "best" is not always so clearly defined. Here, we propose a new and natural solution concept, rooted in game theory, called a von Neumann winner, a randomized policy that beats or ties every other policy. We show that this notion overcomes important limitations of existing solutions, particularly the Condorcet winner which has typically been used in the past, but which requires strong and often unrealistic assumptions. We then present three efficient algorithms for online learning in our setting, and for approximating a von Neumann winner from batch-like data. The first of these algorithms achieves particularly low regret, even when data is adversarial, although its time and space requirements are linear in the size of the policy space. The other two algorithms require time and space only logarithmic in the size of the policy space when provided access to an oracle for solving classification problems on the space.

cs.LG↗

arXiv2015

Incentivizing High Quality Crowdwork

We study the causal effects of financial incentives on the quality of crowdwork. We focus on performance-based payments (PBPs), bonus payments awarded to workers for producing high quality work. We design and run randomized behavioral experiments on the popular crowdsourcing platform Amazon Mechanical Turk with the goal of understanding when, where, and why PBPs help, identifying properties of the payment, payment structure, and the task itself that make them most effective. We provide examples of tasks for which PBPs do improve quality. For such tasks, the effectiveness of PBPs is not too sensitive to the threshold for quality required to receive the bonus, while the magnitude of the bonus must be large enough to make the reward salient. We also present examples of tasks for which PBPs do not improve quality. Our results suggest that for PBPs to improve quality, the task must be effort-responsive: the task must allow workers to produce higher quality work by exerting more effort. We also give a simple method to determine if a task is effort-responsive a priori. Furthermore, our experiments suggest that all payments on Mechanical Turk are, to some degree, implicitly performance-based in that workers believe their work may be rejected if their performance is sufficiently poor. Finally, we propose a new model of worker behavior that extends the standard principal-agent model from economics to include a worker's subjective beliefs about his likelihood of being paid, and show that the predictions of this model are in line with our experimental findings. This model may be useful as a foundation for theoretical studies of incentives in crowdsourcing markets.

cs.GT↗

arXiv2014

Low-distortion Inference of Latent Similarities from a Multiplex Social Network

Much of social network analysis is - implicitly or explicitly - predicated on the assumption that individuals tend to be more similar to their friends than to strangers. Thus, an observed social network provides a noisy signal about the latent underlying "social space:" the way in which individuals are similar or dissimilar. Many research questions frequently addressed via social network analysis are in reality questions about this social space, raising the question of inverting the process: Given a social network, how accurately can we reconstruct the social structure of similarities and dissimilarities? We begin to address this problem formally. Observed social networks are usually multiplex, in the sense that they reflect (dis)similarities in several different "categories," such as geographical proximity, kinship, or similarity of professions/hobbies. We assume that each such category is characterized by a latent metric capturing (dis)similarities in this category. Each category gives rise to a separate social network: a random graph parameterized by this metric. For a concrete model, we consider Kleinberg's small world model and some variations thereof. The observed social network is the unlabeled union of these graphs, i.e., the presence or absence of edges can be observed, but not their origins. Our main result is an algorithm which reconstructs each metric with provably low distortion.

cs.SI↗

arXiv2014

Contextual Bandits with Similarity Information

In a multi-armed bandit (MAB) problem, an online algorithm makes a sequence of choices. In each round it chooses from a time-invariant set of alternatives and receives the payoff associated with this alternative. While the case of small strategy sets is by now well-understood, a lot of recent work has focused on MAB problems with exponentially or infinitely large strategy sets, where one needs to assume extra structure in order to make the problem tractable. In particular, recent literature considered information on similarity between arms. We consider similarity information in the setting of "contextual bandits", a natural extension of the basic MAB problem where before each round an algorithm is given the "context" -- a hint about the payoffs in this round. Contextual bandits are directly motivated by placing advertisements on webpages, one of the crucial problems in sponsored search. A particularly simple way to represent similarity information in the contextual bandit setting is via a "similarity distance" between the context-arm pairs which gives an upper bound on the difference between the respective expected payoffs. Prior work on contextual bandits with similarity uses "uniform" partitions of the similarity space, which is potentially wasteful. We design more efficient algorithms that are based on adaptive partitions adjusted to "popular" context and "high-payoff" arms.

cs.DS↗

arXiv2013

Dynamic Pricing with Limited Supply

We consider the problem of dynamic pricing with limited supply. A seller has $k$ identical items for sale and is facing $n$ potential buyers ("agents") that are arriving sequentially. Each agent is interested in buying one item. Each agent's value for an item is an IID sample from some fixed distribution with support $[0,1]$. The seller offers a take-it-or-leave-it price to each arriving agent (possibly different for different agents), and aims to maximize his expected revenue. We focus on "prior-independent" mechanisms -- ones that do not use any information about the distribution. They are desirable because knowing the distribution is unrealistic in many practical scenarios. We study how the revenue of such mechanisms compares to the revenue of the optimal offline mechanism that knows the distribution ("offline benchmark"). We present a prior-independent dynamic pricing mechanism whose revenue is at most $O((k \log n)^{2/3})$ less than the offline benchmark, for every distribution that is regular. In fact, this guarantee holds without *any* assumptions if the benchmark is relaxed to fixed-price mechanisms. Further, we prove a matching lower bound. The performance guarantee for the same mechanism can be improved to $O(\sqrt{k} \log n)$, with a distribution-dependent constant, if $k/n$ is sufficiently small. We show that, in the worst case over all demand distributions, this is essentially the best rate that can be obtained with a distribution-specific constant. On a technical level, we exploit the connection to multi-armed bandits (MAB). While dynamic pricing with unlimited supply can easily be seen as an MAB problem, the intuition behind MAB approaches breaks when applied to the setting with limited supply. Our high-level conceptual contribution is that even the limited supply setting can be fruitfully treated as a bandit problem.

cs.GT↗

arXiv2013

Online Decision Making in Crowdsourcing Markets: Theoretical Challenges (Position Paper)

Over the past decade, crowdsourcing has emerged as a cheap and efficient method of obtaining solutions to simple tasks that are difficult for computers to solve but possible for humans. The popularity and promise of crowdsourcing markets has led to both empirical and theoretical research on the design of algorithms to optimize various aspects of these markets, such as the pricing and assignment of tasks. Much of the existing theoretical work on crowdsourcing markets has focused on problems that fall into the broad category of online decision making; task requesters or the crowdsourcing platform itself make repeated decisions about prices to set, workers to filter out, problems to assign to specific workers, or other things. Often these decisions are complex, requiring algorithms that learn about the distribution of available tasks or workers over time and take into account the strategic (or sometimes irrational) behavior of workers. As human computation grows into its own field, the time is ripe to address these challenges in a principled way. However, it appears very difficult to capture all pertinent aspects of crowdsourcing markets in a single coherent model. In this paper, we reflect on the modeling issues that inhibit theoretical research on online decision making for crowdsourcing, and identify some steps forward. This paper grew out of the authors' own frustration with these issues, and we hope it will encourage the community to attempt to understand, debate, and ultimately address them. The authors welcome feedback for future revisions of this paper.

cs.SI↗

arXiv2013

Characterizing Truthful Multi-Armed Bandit Mechanisms

We consider a multi-round auction setting motivated by pay-per-click auctions for Internet advertising. In each round the auctioneer selects an advertiser and shows her ad, which is then either clicked or not. An advertiser derives value from clicks; the value of a click is her private information. Initially, neither the auctioneer nor the advertisers have any information about the likelihood of clicks on the advertisements. The auctioneer's goal is to design a (dominant strategies) truthful mechanism that (approximately) maximizes the social welfare. If the advertisers bid their true private values, our problem is equivalent to the "multi-armed bandit problem", and thus can be viewed as a strategic version of the latter. In particular, for both problems the quality of an algorithm can be characterized by "regret", the difference in social welfare between the algorithm and the benchmark which always selects the same "best" advertisement. We investigate how the design of multi-armed bandit algorithms is affected by the restriction that the resulting mechanism must be truthful. We find that truthful mechanisms have certain strong structural properties -- essentially, they must separate exploration from exploitation -- and they incur much higher regret than the optimal multi-armed bandit algorithms. Moreover, we provide a truthful mechanism which (essentially) matches our lower bound on regret.

cs.DS↗

arXiv2013

Dynamic Ad Allocation: Bandits with Budgets

We consider an application of multi-armed bandits to internet advertising (specifically, to dynamic ad allocation in the pay-per-click model, with uncertainty on the click probabilities). We focus on an important practical issue that advertisers are constrained in how much money they can spend on their ad campaigns. This issue has not been considered in the prior work on bandit-based approaches for ad allocation, to the best of our knowledge. We define a simple, stylized model where an algorithm picks one ad to display in each round, and each ad has a \emph{budget}: the maximal amount of money that can be spent on this ad. This model admits a natural variant of UCB1, a well-known algorithm for multi-armed bandits with stochastic rewards. We derive strong provable guarantees for this algorithm.

cs.LG↗

arXiv2013

Adaptive Crowdsourcing Algorithms for the Bandit Survey Problem

Very recently crowdsourcing has become the de facto platform for distributing and collecting human computation for a wide range of tasks and applications such as information retrieval, natural language processing and machine learning. Current crowdsourcing platforms have some limitations in the area of quality control. Most of the effort to ensure good quality has to be done by the experimenter who has to manage the number of workers needed to reach good results. We propose a simple model for adaptive quality control in crowdsourced multiple-choice tasks which we call the \emph{bandit survey problem}. This model is related to, but technically different from the well-known multi-armed bandit problem. We present several algorithms for this problem, and support them with analysis and simulations. Our approach is based in our experience conducting relevance evaluation for a large commercial search engine.

cs.LG↗

arXiv2013

Multi-parameter Mechanisms with Implicit Payment Computation

In this paper we show that payment computation essentially does not present any obstacle in designing truthful mechanisms, even for multi-parameter domains, and even when we can only call the allocation rule once. We present a general reduction that takes any allocation rule which satisfies "cyclic monotonicity" (a known necessary and sufficient condition for truthfulness) and converts it to a truthful mechanism using a single call to the allocation rule, with arbitrarily small loss to the expected social welfare. A prominent example for a multi-parameter setting in which an allocation rule can only be called once arises in sponsored search auctions. These are multi-parameter domains when each advertiser has multiple possible ads he may display, each with a different value per click. Moreover, the mechanism typically does not have complete knowledge of the click-realization or the click-through rates (CTRs); it can only call the allocation rule a single time and observe the click information for ads that were presented. % are not known. On the negative side, we show that an allocation that is truthful for any realization essentially cannot depend on the bids, and hence cannot do better than random selection for one agent. We then consider a relaxed requirement of truthfulness, only in expectation over the CTRs. Even for that relaxed version, making any progress is challenging as standard techniques for construction of truthful mechanisms (as using VCG or an MIDR allocation rule) cannot be used in this setting. We design an allocation rule with non-trivial performance and directly prove it is cyclic-monotone, and thus it can be used to create a truthful mechanism using our general reduction.

cs.GT↗

arXiv2012

Ranked bandits in metric spaces: learning optimally diverse rankings over large document collections

Most learning to rank research has assumed that the utility of different documents is independent, which results in learned ranking functions that return redundant results. The few approaches that avoid this have rather unsatisfyingly lacked theoretical foundations, or do not scale. We present a learning-to-rank formulation that optimizes the fraction of satisfied users, with several scalable algorithms that explicitly takes document similarity and ranking context into account. Our formulation is a non-trivial common generalization of two multi-armed bandit models from the literature: "ranked bandits" (Radlinski et al., ICML 2008) and "Lipschitz bandits" (Kleinberg et al., STOC 2008). We present theoretical justifications for this approach, as well as a near-optimal algorithm. Our evaluation adds optimizations that improve empirical performance, and shows that our algorithms learn orders of magnitude more quickly than previous approaches.

cs.LG↗

arXiv2012

The best of both worlds: stochastic and adversarial bandits

We present a new bandit algorithm, SAO (Stochastic and Adversarial Optimal), whose regret is, essentially, optimal both for adversarial rewards and for stochastic rewards. Specifically, SAO combines the square-root worst-case regret of Exp3 (Auer et al., SIAM J. on Computing 2002) and the (poly)logarithmic regret of UCB1 (Auer et al., Machine Learning 2002) for stochastic rewards. Adversarial rewards and stochastic rewards are the two main settings in the literature on (non-Bayesian) multi-armed bandits. Prior work on multi-armed bandits treats them separately, and does not attempt to jointly optimize for both. Our result falls into a general theme of achieving good worst-case performance while also taking advantage of "nice" problem instances, an important issue in the design of algorithms with partially known inputs.

cs.LG↗

arXiv2010

Adapting to the Shifting Intent of Search Queries

Search engines today present results that are often oblivious to abrupt shifts in intent. For example, the query `independence day' usually refers to a US holiday, but the intent of this query abruptly changed during the release of a major film by that name. While no studies exactly quantify the magnitude of intent-shifting traffic, studies suggest that news events, seasonal topics, pop culture, etc account for 50% of all search queries. This paper shows that the signals a search engine receives can be used to both determine that a shift in intent has happened, as well as find a result that is now more relevant. We present a meta-algorithm that marries a classifier with a bandit algorithm to achieve regret that depends logarithmically on the number of query impressions, under certain assumptions. We provide strong evidence that this regret is close to the best achievable. Finally, via a series of experiments, we demonstrate that our algorithm outperforms prior approaches, particularly as the amount of intent-shifting traffic increases.

cs.LG↗

arXiv2009

Sharp Dichotomies for Regret Minimization in Metric Spaces

The Lipschitz multi-armed bandit (MAB) problem generalizes the classical multi-armed bandit problem by assuming one is given side information consisting of a priori upper bounds on the difference in expected payoff between certain pairs of strategies. Classical results of (Lai and Robbins 1985) and (Auer et al. 2002) imply a logarithmic regret bound for the Lipschitz MAB problem on finite metric spaces. Recent results on continuum-armed bandit problems and their generalizations imply lower bounds of $\sqrt{t}$, or stronger, for many infinite metric spaces such as the unit interval. Is this dichotomy universal? We prove that the answer is yes: for every metric space, the optimal regret of a Lipschitz MAB algorithm is either bounded above by any $f\in ω(\log t)$, or bounded below by any $g\in o(\sqrt{t})$. Perhaps surprisingly, this dichotomy does not coincide with the distinction between finite and infinite metric spaces; instead it depends on whether the completion of the metric space is compact and countable. Our proof connects upper and lower bound techniques in online learning with classical topological notions such as perfect sets and the Cantor-Bendixson theorem. Among many other results, we show a similar dichotomy for the "full-feedback" (a.k.a., "best-expert") version.

cs.DS↗

arXiv2008

Oscillations with TCP-like Flow Control in Networks of Queues

We consider a set of flows passing through a set of servers. The injection rate into each flow is governed by a flow control that increases the injection rate when all the servers on the flow's path are empty and decreases the injection rate when some server is congested. We show that if each server's congestion is governed by the arriving traffic at the server then the system can *oscillate*. This is in contrast to previous work on flow control where congestion was modeled as a function of the flow injection rates and the system was shown to converge to a steady state that maximizes an overall network utility.

cs.NI↗

arXiv2008

Multi-Armed Bandits in Metric Spaces

In a multi-armed bandit problem, an online algorithm chooses from a set of strategies in a sequence of trials so as to maximize the total payoff of the chosen strategies. While the performance of bandit algorithms with a small finite strategy set is quite well understood, bandit problems with large strategy sets are still a topic of very active investigation, motivated by practical applications such as online auctions and web advertisement. The goal of such research is to identify broad and natural classes of strategy sets and payoff functions which enable the design of efficient solutions. In this work we study a very general setting for the multi-armed bandit problem in which the strategies form a metric space, and the payoff function satisfies a Lipschitz condition with respect to the metric. We refer to this problem as the "Lipschitz MAB problem". We present a complete solution for the multi-armed problem in this setting. That is, for every metric space (L,X) we define an isometry invariant which bounds from below the performance of Lipschitz MAB algorithms for X, and we present an algorithm which comes arbitrarily close to meeting this bound. Furthermore, our technique gives even better results for benign payoff functions.

cs.DS↗