Searcharxiv⌕ Search

arXiv subjects

Mihaela van der Schaar

Publications and source records attributed to Mihaela van der Schaar.

At least 325 records · Page 18Linked to original sources
arXiv2013

Decentralized Online Big Data Classification - a Bandit Framework

Distributed, online data mining systems have emerged as a result of applications requiring analysis of large amounts of correlated and high-dimensional data produced by multiple distributed data sources. We propose a distributed online data classification framework where data is gathered by distributed data sources and processed by a heterogeneous set of distributed learners which learn online, at run-time, how to classify the different data streams either by using their locally available classification functions or by helping each other by classifying each other's data. Importantly, since the data is gathered at different locations, sending the data to another learner to process incurs additional costs such as delays, and hence this will be only beneficial if the benefits obtained from a better classification will exceed the costs. We assume that the classification functions available to each processing element are fixed, but their prediction accuracy for various types of incoming data are unknown and can change dynamically over time, and thus they need to be learned online. We model the problem of joint classification by the distributed and heterogeneous learners from multiple data sources as a distributed contextual bandit problem where each data is characterized by a specific context. We develop distributed online learning algorithms for which we can prove that they have sublinear regret. Compared to prior work in distributed online data mining, our work is the first to provide analytic regret results characterizing the performance of the proposed algorithms.

cs.LG↗
arXiv2013

Ensemble of Distributed Learners for Online Classification of Dynamic Data Streams

We present an efficient distributed online learning scheme to classify data captured from distributed, heterogeneous, and dynamic data sources. Our scheme consists of multiple distributed local learners, that analyze different streams of data that are correlated to a common event that needs to be classified. Each learner uses a local classifier to make a local prediction. The local predictions are then collected by each learner and combined using a weighted majority rule to output the final prediction. We propose a novel online ensemble learning algorithm to update the aggregation rule in order to adapt to the underlying data dynamics. We rigorously determine a bound for the worst case misclassification probability of our algorithm which depends on the misclassification probabilities of the best static aggregation rule, and of the best local classifier. Importantly, the worst case misclassification probability of our algorithm tends asymptotically to 0 if the misclassification probability of the best static aggregation rule or the misclassification probability of the best local classifier tend to 0. Then we extend our algorithm to address challenges specific to the distributed implementation and we prove new bounds that apply to these settings. Finally, we test our scheme by performing an evaluation study on several data sets. When applied to data sets widely used by the literature dealing with dynamic data streams and concept drift, our scheme exhibits performance gains ranging from 34% to 71% with respect to state of the art solutions.

cs.LG↗
arXiv2013

Distributed Online Big Data Classification Using Context Information

Distributed, online data mining systems have emerged as a result of applications requiring analysis of large amounts of correlated and high-dimensional data produced by multiple distributed data sources. We propose a distributed online data classification framework where data is gathered by distributed data sources and processed by a heterogeneous set of distributed learners which learn online, at run-time, how to classify the different data streams either by using their locally available classification functions or by helping each other by classifying each other's data. Importantly, since the data is gathered at different locations, sending the data to another learner to process incurs additional costs such as delays, and hence this will be only beneficial if the benefits obtained from a better classification will exceed the costs. We model the problem of joint classification by the distributed and heterogeneous learners from multiple data sources as a distributed contextual bandit problem where each data is characterized by a specific context. We develop a distributed online learning algorithm for which we can prove sublinear regret. Compared to prior work in distributed online data mining, our work is the first to provide analytic regret results characterizing the performance of the proposed algorithm.

cs.LG↗
arXiv2013

Fast Reinforcement Learning for Energy-Efficient Wireless Communications

We consider the problem of energy-efficient point-to-point transmission of delay-sensitive data (e.g. multimedia data) over a fading channel. Existing research on this topic utilizes either physical-layer centric solutions, namely power-control and adaptive modulation and coding (AMC), or system-level solutions based on dynamic power management (DPM); however, there is currently no rigorous and unified framework for simultaneously utilizing both physical-layer centric and system-level techniques to achieve the minimum possible energy consumption, under delay constraints, in the presence of stochastic and a priori unknown traffic and channel conditions. In this report, we propose such a framework. We formulate the stochastic optimization problem as a Markov decision process (MDP) and solve it online using reinforcement learning. The advantages of the proposed online method are that (i) it does not require a priori knowledge of the traffic arrival and channel statistics to determine the jointly optimal power-control, AMC, and DPM policies; (ii) it exploits partial information about the system so that less information needs to be learned than when using conventional reinforcement learning algorithms; and (iii) it obviates the need for action exploration, which severely limits the adaptation speed and run-time performance of conventional reinforcement learning algorithms. Our results show that the proposed learning algorithms can converge up to two orders of magnitude faster than a state-of-the-art learning algorithm for physical layer power-control and up to three orders of magnitude faster than conventional reinforcement learning algorithms.

cs.LG↗
arXiv2012

Pricing and Intervention in Slotted-Aloha: Technical Report

In many wireless communication networks a common channel is shared by multiple users who must compete to gain access to it. The operation of the network by self-interested and strategic users usually leads to the overuse of the channel resources and to substantial inefficiencies. Hence, incentive schemes are needed to overcome the inefficiencies of non-cooperative equilibrium. In this work we consider a slotted-Aloha like random access protocol and two incentive schemes: pricing and intervention. We provide some criteria for the designer of the protocol to choose one scheme between them and to design the best policy for the selected scheme, depending on the system parameters. Our results show that intervention can achieve the maximum efficiency in the perfect monitoring scenario. In the imperfect monitoring scenario, instead, the performance of the system depends on the information held by the different entities and, in some cases, there exists a threshold for the number of users such that, for a number of users lower than the threshold, intervention outperforms pricing, whereas, for a number of users higher than the threshold pricing outperforms intervention.

cs.GT↗
arXiv2012

Social Norm Design for Information Exchange Systems with Limited Observations

Information exchange systems differ in many ways, but all share a common vulnerability to selfish behavior and free-riding. In this paper, we build incentives schemes based on social norms. Social norms prescribe a social strategy for the users in the system to follow and deploy reputation schemes to reward or penalize users depending on their behaviors. Because users in these systems often have only limited capability to observe the global system information, e.g. the reputation distribution of the users participating in the system, their beliefs about the reputation distribution are heterogeneous and biased. Such belief heterogeneity causes a positive fraction of users to not follow the social strategy. In such practical scenarios, the standard equilibrium analysis deployed in the economics literature is no longer directly applicable and hence, the system design needs to consider these differences. To investigate how the system designs need to change when the participating users have only limited observations, we focus on a simple social norm with binary reputation labels but allow adjusting the punishment severity through randomization. First, we model the belief heterogeneity using a suitable Bayesian belief function. Next, we formalize the users' optimal decision problems and derive in which scenarios they follow the prescribed social strategy. With this result, we then study the system dynamics and formally define equilibrium in the sense that the system is stable when users strategically optimize their decisions. By rigorously studying two specific cases where users' belief distribution is constant or is linearly influenced by the true reputation distribution, we prove that the optimal reputation update rule is to choose the mildest possible punishment. This result is further confirmed for higher order beliefs in simulations.

cs.GT↗
arXiv2012

Designing Rating Systems to Promote Mutual Security for Interconnected Networks

Interconnected autonomous systems often share security risks. However, an autonomous system lacks the incentive to make (sufficient) security investments if the cost exceeds its own benefit even though doing that would be socially beneficial. In this paper, we develop a systematic and rigorous framework for analyzing and significantly improving the mutual security of a collection of ASs that interact frequently over a long period of time. Using this framework, we show that simple incentive schemes based on rating systems can be designed to encourage the autonomous systems' security investments, thereby significantly improving their mutual security.

cs.GT↗
arXiv2012

Technology Choices and Pricing Policies in Public and Private Wireless Networks

This paper studies the provision of a wireless network by a monopolistic provider who may be either benevolent (seeking to maximize social welfare) or selfish (seeking to maximize provider profit). The paper addresses questions that do not seem to have been studied before in the engineering literature on wireless networks: Under what circumstances is it feasible for a provider, either benevolent or selfish, to operate a network in such a way as to cover costs? How is the optimal behavior of a benevolent provider different from the optimal behavior of a selfish provider, and how does this difference affect social welfare? And, most importantly, how does the medium access control (MAC) technology influence the answers to these questions? To address these questions, we build a general model, and provide analysis and simulations for simplified but typical scenarios; the focus in these scenarios is on the contrast between the outcomes obtained under carrier-sensing multiple access (CSMA) and outcomes obtained under time-division multiple access (TDMA). Simulation results demonstrate that differences in MAC technology can have a significant effect on social welfare, on provider profit, and even on the (financial) feasibility of a wireless network.

cs.GT↗
arXiv2012

Dynamic Spectrum Sharing Among Repeatedly Interacting Selfish Users With Imperfect Monitoring

We develop a novel design framework for dynamic distributed spectrum sharing among secondary users (SUs) who adjust their power levels to compete for spectrum opportunities while satisfying the interference temperature (IT) constraints imposed by primary users. The considered interaction among the SUs is characterized by the following three features. First, since the SUs are decentralized, they are selfish and aim to maximize their own long-term payoffs from utilizing the network rather than obeying the prescribed allocation of a centralized controller. Second, the SUs interact with each other repeatedly and they can coexist in the system for a long time. Third, the SUs have limited and imperfect monitoring ability: they only observe whether the IT constraints are violated, and their observation is imperfect due to the erroneous measurements. To capture these features, we model the interaction of the SUs as a repeated game with imperfect monitoring. We first characterize the set of Pareto optimal payoffs that can be achieved by deviation-proof spectrum sharing policies, which are policies that the selfish users find it in their interest to comply with. Next, for any given payoff in this set, we show how to construct a deviation-proof policy to achieve it. The constructed deviation-proof policy is amenable to distributed implementation, and allows users to transmit in a time-division multiple-access (TDMA) fashion. In the presence of strong multi-user interference, our policy outperforms existing spectrum sharing policies that dictate users to transmit at constant power levels simultaneously. Moreover, our policy can achieve Pareto optimality even when the SUs have limited and imperfect monitoring ability, as opposed to existing solutions based on repeated games, which require perfect monitoring abilities.

cs.IT↗
arXiv2012

Designing Practical Distributed Exchange for Online Communities

In many online systems, individuals provide services for each other; the recipient of the service obtains a benefit but the provider of the service incurs a cost. If benefit exceeds cost, provision of the service increases social welfare and should therefore be encouraged -- but the individuals providing the service gain no (immediate) benefit from providing the service and hence have an incentive to withhold service. Hence there is scope for designing a system that improves welfare by encouraging exchange. To operate successfully within the confines of the online environment, such a system should be distributed, practicable, and consistent with individual incentives. This paper proposes and analyzes a simple such system that relies on the exchange of {\em tokens}; the emphasis is on the design of a protocol (number of tokens and suggested strategies). We provide estimates for the efficiency of such protocols and show that choosing the right protocol will lead to almost full efficiency if agents are sufficiently patient. However, choosing the wrong protocols may lead to an enormous loss of efficiency.

cs.GT↗
arXiv2012

Designing Information Revelation and Intervention with an Application to Flow Control

There are many familiar situations in which a manager seeks to design a system in which users share a resource, but outcomes depend on the information held and actions taken by users. If communication is possible, the manager can ask users to report their private information and then, using this information, instruct them on what actions they should take. If the users are compliant, this reduces the manager's optimization problem to a well-studied problem of optimal control. However, if the users are self-interested and not compliant, the problem is much more complicated: when asked to report their private information, the users might lie; upon receiving instructions, the users might disobey. Here we ask whether the manager can design the system to get around both of these difficulties. To do so, the manager must provide for the users the incentives to report truthfully and to follow the instructions, despite the fact that the users are self-interested. For a class of environments that includes many resource allocation games in communication networks, we provide tools for the manager to design an efficient system. In addition to reports and recommendations, the design we employ allows the manager to intervene in the system after the users take actions. In an abstracted environment, we find conditions under which the manager can achieve the same outcome it could if users were compliant, and conditions under which it does not. We then apply our framework and results to design a flow control management system.

cs.GT↗
arXiv2012

Markov Decision Process Based Energy-Efficient On-Line Scheduling for Slice-Parallel Video Decoders on Multicore Systems

We consider the problem of energy-efficient on-line scheduling for slice-parallel video decoders on multicore systems. We assume that each of the processors are Dynamic Voltage Frequency Scaling (DVFS) enabled such that they can independently trade off performance for power, while taking the video decoding workload into account. In the past, scheduling and DVFS policies in multi-core systems have been formulated heuristically due to the inherent complexity of the on-line multicore scheduling problem. The key contribution of this report is that we rigorously formulate the problem as a Markov decision process (MDP), which simultaneously takes into account the on-line scheduling and per-core DVFS capabilities; the power consumption of the processor cores and caches; and the loss tolerant and dynamic nature of the video decoder's traffic. In particular, we model the video traffic using a Direct Acyclic Graph (DAG) to capture the precedence constraints among frames in a Group of Pictures (GOP) structure, while also accounting for the fact that frames have different display/decoding deadlines and non-deterministic decoding complexities. The objective of the MDP is to minimize long-term power consumption subject to a minimum Quality of Service (QoS) constraint related to the decoder's throughput. Although MDPs notoriously suffer from the curse of dimensionality, we show that, with appropriate simplifications and approximations, the complexity of the MDP can be mitigated. We implement a slice-parallel version of H.264 on a multiprocessor ARM (MPARM) virtual platform simulator, which provides cycle-accurate and bus signal-accurate simulation for different processors. We use this platform to generate realistic video decoding traces with which we evaluate the proposed on-line scheduling algorithm in Matlab.

cs.MM↗
arXiv2012

Entry and Spectrum Sharing Scheme Selection in Femtocell Markets

Focusing on a femtocell communications market, we study the entrant network service provider's (NSP's) long-term decision: whether to enter the market and which spectrum sharing technology to select to maximize its profit. This long-term decision is closely related to the entrant's pricing strategy and the users' aggregate demand, which we model as medium-term and short-term decisions, respectively. We consider two markets, one with no incumbent and the other with one incumbent. For both markets, we show the existence and uniqueness of an equilibrium point in the user subscription dynamics, and provide a sufficient condition for the convergence of the dynamics. For the market with no incumbent, we derive upper and lower bounds on the optimal price and market share that maximize the entrant's revenue, based on which the entrant selects an available technology to maximize its long-term profit. For the market with one incumbent, we model competition between the two NSPs as a non-cooperative game, in which the incumbent and the entrant choose their market shares independently, and provide a sufficient condition that guarantees the existence of at least one pure Nash equilibrium. Finally, we formalize the problem of entry and spectrum sharing scheme selection for the entrant and provide numerical results to complement our analysis.

cs.GT↗
arXiv2011

Intervention in Power Control Games With Selfish Users

We study the power control problem in wireless ad hoc networks with selfish users. Without incentive schemes, selfish users tend to transmit at their maximum power levels, causing significant interference to each other. In this paper, we study a class of incentive schemes based on intervention to induce selfish users to transmit at desired power levels. An intervention scheme can be implemented by introducing an intervention device that can monitor the power levels of users and then transmit power to cause interference to users. We mainly consider first-order intervention rules based on individual transmit powers. We derive conditions on design parameters and the intervention capability to achieve a desired outcome as a (unique) Nash equilibrium and propose a dynamic adjustment process that the designer can use to guide users and the intervention device to the desired outcome. The effect of using intervention rules based on aggregate receive power is also analyzed. Our results show that with perfect monitoring intervention schemes can be designed to achieve any positive power profile while using interference from the intervention device only as a threat. We also analyze the case of imperfect monitoring and show that a performance loss can occur. Lastly, simulation results are presented to illustrate the performance improvement from using intervention rules and compare the performances of different intervention rules.

cs.IT↗
arXiv2011

Repeated Games With Intervention: Theory and Applications in Communications

In communication systems where users share common resources, users' selfish behavior usually results in suboptimal resource utilization. There have been extensive works that model communication systems with selfish users as one-shot games and propose incentive schemes to achieve Pareto optimal action profiles as non-cooperative equilibria. However, in many communication systems, due to strong negative externalities among users, the sets of feasible payoffs in one-shot games are nonconvex. Thus, it is possible to expand the set of feasible payoffs by having users choose convex combinations of different payoffs. In this paper, we propose a repeated game model generalized by intervention. First, we use repeated games to convexify the set of feasible payoffs in one-shot games. Second, we combine conventional repeated games with intervention, originally proposed for one-shot games, to achieve a larger set of equilibrium payoffs and loosen requirements for users' patience to achieve it. We study the problem of maximizing a welfare function defined on users' equilibrium payoffs, subject to minimum payoff guarantees. Given the optimal equilibrium payoff, we derive the minimum intervention capability required and design corresponding equilibrium strategies. The proposed generalized repeated game model applies to various communication systems, such as power control and flow control.

cs.IT↗
arXiv2011

Transmitting important bits and sailing high radio waves: a decentralized cross-layer approach to cooperative video transmission

We investigate the impact of cooperative relaying on uplink and downlink multi-user (MU) wireless video transmissions. The objective is to maximize the long-term sum of utilities across the video terminals in a decentralized fashion, by jointly optimizing the packet scheduling, the resource allocation, and the cooperation decisions, under the assumption that some nodes are willing to act as cooperative relays. A pricing-based distributed resource allocation framework is adopted, where the price reflects the expected future congestion in the network. Specifically, we formulate the wireless video transmission problem as an MU Markov decision process (MDP) that explicitly considers the cooperation at the physical layer and the medium access control sublayer, the video users' heterogeneous traffic characteristics, the dynamically varying network conditions, and the coupling among the users' transmission strategies across time due to the shared wireless resource. Although MDPs notoriously suffer from the curse of dimensionality, our study shows that, with appropriate simplications and approximations, the complexity of the MU-MDP can be significantly mitigated. Our simulation results demonstrate that integrating cooperative decisions into the MU-MDP optimization can increase the resource price in networks that only support low transmission rates and can decrease the price in networks that support high transmission rates. Additionally, our results show that cooperation allows users with feeble direct signals to achieve improvements in video quality on the order of 5-10 dB peak signal-to-noise ratio (PSNR), with less than 0.8 dB quality loss by users with strong direct signals, and with a moderate increase in total network energy consumption that is significantly less than the energy that a distant node would require to achieve an equivalent PSNR without exploiting cooperative diversity.

cs.MM↗
arXiv2011

Production and Network Formation Games with Content Heterogeneity

Online social networks (e.g. Facebook, Twitter, Youtube) provide a popular, cost-effective and scalable framework for sharing user-generated contents. This paper addresses the intrinsic incentive problems residing in social networks using a game-theoretic model where individual users selfishly trade off the costs of forming links (i.e. whom they interact with) and producing contents personally against the potential rewards from doing so. Departing from the assumption that contents produced by difference users is perfectly substitutable, we explicitly consider heterogeneity in user-generated contents and study how it influences users' behavior and the structure of social networks. Given content heterogeneity, we rigorously prove that when the population of a social network is sufficiently large, every (strict) non-cooperative equilibrium should consist of either a symmetric network topology where each user produces the same amount of content and has the same degree, or a two-level hierarchical topology with all users belonging to either of the two types: influencers who produce large amounts of contents and subscribers who produce small amounts of contents and get most of their contents from influencers. Meanwhile, the law of the few disappears in such networks. Moreover, we prove that the social optimum is always achieved by networks with symmetric topologies, where the sum of users' utilities is maximized. To provide users with incentives for producing and mutually sharing the socially optimal amount of contents, a pricing scheme is proposed, with which we show that the social optimum can be achieved as a non-cooperative equilibrium with the pricing of content acquisition and link formation.

cs.SI↗