Abstract

Machine learning models are extensively being used in decision making, especially for prediction tasks. These models could be biased or unfair towards a specific sensitive group either of a specific race, gender or age. Researchers have put efforts into characterizing a particular definition of fairness and enforcing them into the models. In this work, mainly we are concerned with the following three definitions, Disparate Impact, Demographic Parity and Equalized Odds. Researchers have shown that Equalized Odds cannot be satisfied in calibrated classifiers unless the classifier is perfect. Hence the primary challenge is to ensure a degree of fairness while guaranteeing as much accuracy as possible. Fairness constraints are complex and need not be convex. Incorporating them into a machine learning algorithm is a significant challenge. Hence, many researchers have tried to come up with a surrogate loss which is convex in order to build fair classifiers. Besides, certain papers try to build fair representations by preprocessing the data, irrespective of the classifier used. Such methods, not only require a lot of unrealistic assumptions but also require human engineered analytical solutions to build a machine learning model. We instead propose an automated solution which is generalizable over any fairness constraint. We use a neural network which is trained on batches and directly enforces the fairness constraint as the loss function without modifying it further. We have also experimented with other complex performance measures such as H-mean loss, Q-mean-loss, F-measure; without the need for any surrogate loss functions. Our experiments …

Abstract

There are numerous situations when a service requester wishes to expertsourcea series of identical but non-trivial tasks from a pool of experts so as to achieve an assured accuracy level for each task, in a cost optimal way. The experts available are typically heterogeneous with unknown but fixed qualities and different service costs. The service costs are usually private to the experts and the experts could be strategic about their costs. The problem is to select for each task an optimal subset of experts so that the outcome obtained after aggregating the opinions from the selected experts guarantees a target level of accuracy. The problem is a challenging one even in a non-strategic setting since the accuracy of an aggregated outcome depends on unknown qualities. We develop a novel multi-armed bandit (MAB) mechanism for solving this problem. First, we propose a framework, Assured Accuracy Bandit (AAB)framework, which leads to a MAB algorithm, Constrained Confidence Bound for Non-Strategic Setting (CCB-NS). We derive an upper bound on the number of time steps this algorithm chooses a sub-optimal set, which depends on the target accuracy and true qualities. A more challenging situation arises when the requester not only has to learn the qualities of the experts but has to elicit their true service costs as well. We modify the CCB-NS algorithm to obtain an adaptive exploration separated algorithm Constrained Confidence Bound for Strategic Setting (CCB-S). The CCB-S algorithm produces an ex-post monotone allocation rule that can then be transformed into an ex-post incentive compatible and ex-post individually rational mechanism. This mechanism learns the qualities of the experts and guarantees a given target accuracy level in a cost optimal way. We also provide a lower bound on the number of times any algorithm must select a sub-optimal set and we see that the lower bound matches our upper bound up to a constant factor. We provide insights on a practical implementation of this framework through an illustrative example and demonstrate the efficacy of our algorithms through simulations

Abstract

The popularity of digital currencies, especially cryptocurrencies, has been continuously growing since the appearance of Bitcoin. Bitcoin’s security lies in a proof-of-work scheme, which requires high computational resources at the miners. Despite advances in mobile technology, existing cryptocurrencies cannot be maintained by mobile devices due to their low processing capabilities. Mobile devices can only accommodate mobile applications (wallets) that allow users to exchange credits of cryptocurrencies. In this work, we propose LocalCoin, an alternative cryptocurrency that requires minimal computational resources, produces low data traffic and works with off-the-shelf mobile devices. LocalCoin replaces the computational hardness that is at the root of Bitcoin’s security with the social hardness of ensuring that all witnesses to a transaction are colluders. Localcoin features (i) a lightweight proof-of-work scheme and (ii) a distributed blockchain. We analyze LocalCoin for double spending for passive and active attacks and prove that under the assumption of sufficient number of users and properly selected tuning parameters the probability of double spending is close to zero. Extensive simulations on real mobility traces, realistic urban settings, and random geometric graphs show that the probability of success of one transaction converges to 1 and the probability of the success of a double spending attempt converges to 0.

Abstract

The popularity of digital currencies, especially cryptocurrencies, has been continuously growing since the appearance of Bitcoin. Bitcoin’s security lies in a proof-of-work scheme, which requires high computational resources at the miners. Despite advances in mobile technology, existing cryptocurrencies cannot be maintained by mobile devices due to their low processing capabilities. Mobile devices can only accommodate mobile applications (wallets) that allow users to exchange credits of cryptocurrencies. In this work, we propose LocalCoin, an alternative cryptocurrency that requires minimal computational resources, produces low data traffic and works with off-the-shelf mobile devices. LocalCoin replaces the computational hardness that is at the root of Bitcoin’s security with the social hardness of ensuring that all witnesses to a transaction are colluders. Localcoin features (i) a lightweight proof-of-work scheme and (ii) a distributed blockchain. We analyze LocalCoin for double spending for passive and active attacks and prove that under the assumption of sufficient number of users and properly selected tuning parameters the probability of double spending is close to zero. Extensive simulations on real mobility traces, realistic urban settings, and random geometric graphs show that the probability of success of one transaction converges to 1 and the probability of the success of a double spending attempt converges to 0.

Abstract

This paper explores Thompson sampling in the context of mechanism design for stochastic multi-armed bandit (MAB) problems. The setting is that of an MAB problem where the reward distribution of each arm consists of a stochastic component as well as a strategic component. Many existing MAB mechanisms use upper confidence bound (UCB) based algorithms for learning the parameters of the reward distribution. The randomized nature of Thompson sampling introduces certain unique, non-trivial challenges for mechanism design, which we address in this paper through a rigorous regret analysis. We first propose a MAB mechanism with deterministic payment rule, namely, TSM-D. We show that in TSMD, the variance of agent utilities asymptotically approaches zero. However, the game theoretic properties satisfied by TSM-D (incentive compatibility and individual rationality with high probability) are rather weak. As our main contribution, we then propose the mechanism TSM-R, with randomized payment rule, and prove that TSM-R satisfies appropriate, adequate notions of incentive compatibility and individual rationality. For TSM-R, we also establish a theoretical upper bound on the variance in utilities of the agents. We further show, using simulations, that the variance in social welfare incurred by TSM-D or TSM-R is much lower when compared to that of existing UCB based mechanisms. We believe this paper establishes Thompson sampling as an attractive approach to be used in MAB mechanism design.

Abstract

Dynamic resource assignment is a common problem in multi-agent systems. We consider scenarios in which dynamic agents have preferences about assignments and the resources that can be assigned using online auctions. We study the trade-off between the following online auction properties: (i) truthfulness, (ii) expressiveness, (iii) efficiency, and (iv) average case performance. We theoretically and empirically compare four different online auctions: (i) Arrival Priority Serial Dictatorship, (ii) Split Dynamic VCG, (iii) e-Action, and (iv) Online Ranked Competition Auction. The latter is a novel design based on the competitive secretary problem. We show that, in addition to truthfulness and algorithmic efficiency, the degree of competition also plays an important role in selecting the best algorithm for a given context

Abstract

We consider a general crowdsourcing setting with strategic workers whose qualities are unknown and design a multiarmed bandit (MAB) mechanism, CrowdUCB, which is deterministic, regret minimizing, and offers immediate payments to the workers. The problem involves sequentially selecting workers to process tasks in order to maximize the social welfare while learning the qualities of the strategic workers (strategic about their costs). Existing MAB mechanisms are either: (a) deterministic which potentially cause significant loss in social welfare, or (b) randomized which typically lead to high variance in payments. CrowdUCB completely addresses the above problems with the following features: (i) offers deterministic payments, (ii) achieves logarithmic regret in social welfare, (iii) renders allocations more effective by allocating blocks of tasks to a worker instead of a single task, and (iv) offers payment to a worker immediately upon completion of an assigned block of tasks. CrowdUCB is a mechanism with learning that learns the qualities of the workers while eliciting their true costs, irrespective of whether or not the workers know their own qualities. We show that CrowdUCB is ex-post individually rational (EPIR) and ex-post incentive compatible (EPIC) when the workers do not know their own qualities and when they update their beliefs in sync with the requester. When the workers know their own qualities, CrowdUCB is EPIR and ε−EPIC where ε is sub-linear in terms of the number of tasks.

Abstract

Crowdfunding is emerging as a popular means to generate funding from citizens for public projects. This is popularly known as civic crowdfunding. In this paper, we focus on crowdfunding public projects with provision point: these are projects in which contributions must reach a predetermined threshold in order for the project to be provisioned. On web based civic crowdfunding platforms, the success of crowdfunding public projects has been somewhat mixed. In this paper, our objective is to design a mechanism that improves the success of crowdfunding public projects. In particular, we propose a class of mechanisms for crowdfunding platforms with sequentially arriving agents. This class of mechanisms induces an extensive form game for agents arriving on the platform and we show that the game has a non-empty set of sub-game perfect equilibria at which the project is fully funded. We call this new class of mechanisms Provision Point Mechanism with Securities (PPS). The novelty of PPS lies in the use of a prediction market to incentivize agents to contribute in proportion to their true value for the project and to contribute as soon as they arrive at the crowdfunding platform. Different variations of PPS are possible depending on the underlying prediction market. In this paper, we use a cost function (or equivalently, scoring rule) based prediction market; in fact, we specify the requirements that a cost function should satisfy to be used in PPS. We study and compare two specific instances of PPS: (1) Logarithmic Market Scoring Rule based and (2) Quadratic Scoring Rule based. We also discuss the considerations that should guide the choice of the cost function when deploying our mechanism on crowdfunding platforms

Abstract

Motivated by web based marketplaces where the number of bidders in an auction is a small subset of potential bidders, we consider auctions where the auctioneer (seller) wishes to increase her revenue and/or social welfare by expanding the pool of participants. To this end, the seller crowdsources this task by offering a referral bonus to the participants. With the introduction of referrals, a participant can now bid and/or refer other agents to bid. We call our auctions crowdsourced referral auctions since the seller exploits the knowledge that agents have about other potential participants in the crowd. We introduce the notion of price of locality to quantify the loss in social welfare due to restricted (local) access of the seller to potential bidders. We introduce the notion of Crowdsourced Referral Auction Mechanisms (CRAMs), propose two novel versions of CRAMs and study the induced referral game in the canonical context of an auction for selling a single indivisible item. We compare their revenue performance and game theoretic properties and show that both of them outperform the baseline auction without referrals

Abstract

Civic Crowdfunding is emerging as a popular means to mobilize funding from citizens for public projects. A popular mechanism deployed on civic crowdfunding platforms is a provision point mechanism, wherein, the total contributions must reach a predetermined threshold in order for the project to be provisioned (undertaken). Such a mechanism may have multiple equilibria; unfortunately, in many of these equilibria, the project is not funded even if it is highly valued among the agents.Recent work has proposed mechanisms with refund bonuses where the project gets funded in equilibrium if its net value is higher than a threshold among the agents who are aware of the crowdfunding effort. In this paper, we formalize the notion of social desirability of a public project and propose mechanisms which use the idea of referrals to expand the pool of participants and achieve an equilibrium in which the project gets funded if its net value exceeds a threshold among the entire agent population. We call this new class of mechanisms Referral-Embedded Provision Point Mechanisms (REPPM). We specifically propose two variants of REPPM and both these mechanisms have the remarkable property that, at equilibrium, referral bonuses are offered but there is no need for actual payment of these bonuses. We establish that any given agent’s equilibrium strategy is to refer other agents and to contribute in proportion to the agent’s true value for the project. By referring others to contribute, an agent can, in fact, reduce his equilibrium contribution. In our view, the proposed mechanisms will lead to an increase in the number of projects that are funded on civic crowdfunding platforms.