arXiv subjects

Sampath Kannan

Publications and source records attributed to Sampath Kannan.

23 records · Page 2Linked to original sources

arXiv2015

Private Pareto Optimal Exchange

We consider the problem of implementing an individually rational, asymptotically Pareto optimal allocation in a barter-exchange economy where agents are endowed with goods and have preferences over the goods of others, but may not use money as a medium of exchange. Because one of the most important instantiations of such economies is kidney exchange -- where the "input"to the problem consists of sensitive patient medical records -- we ask to what extent such exchanges can be carried out while providing formal privacy guarantees to the participants. We show that individually rational allocations cannot achieve any non-trivial approximation to Pareto optimality if carried out under the constraint of differential privacy -- or even the relaxation of \emph{joint} differential privacy, under which it is known that asymptotically optimal allocations can be computed in two-sided markets, where there is a distinction between buyers and sellers and we are concerned only with privacy of the buyers~\citep{Matching}. We therefore consider a further relaxation that we call \emph{marginal} differential privacy -- which promises, informally, that the privacy of every agent $i$ is protected from every other agent $j \neq i$ so long as $j$ does not collude or share allocation information with other agents. We show that, under marginal differential privacy, it is possible to compute an individually rational and asymptotically Pareto optimal allocation in such exchange economies.

cs.GT↗

arXiv2014

Variance on the Leaves of a Tree Markov Random Field: Detecting Character Dependencies in Phylogenies

Stochastic models of evolution (Markov random fields on trivalent trees) generally assume that different characters (different runs of the stochastic process) are independent and identically distributed. In this paper we take the first steps towards addressing dependent characters. Specifically we show that, under certain technical assumptions regarding the evolution of individual characters, we can detect any significant, history independent, correlation between any pair of multistate characters. For the special case of the Cavender-Farris-Neyman (CFN) model on two states with symmetric transition matrices, our analysis needs milder assumptions. To perform the analysis, we need to prove a new concentration result for multistate random variables of a Markov random field on arbitrary trivalent trees: we show that the random variable counting the number of leaves in any particular subset of states has variance that is subquadratic in the number of leaves.

q-bio.PE↗

arXiv2014

Approximately Stable, School Optimal, and Student-Truthful Many-to-One Matchings (via Differential Privacy)

We present a mechanism for computing asymptotically stable school optimal matchings, while guaranteeing that it is an asymptotic dominant strategy for every student to report their true preferences to the mechanism. Our main tool in this endeavor is differential privacy: we give an algorithm that coordinates a stable matching using differentially private signals, which lead to our truthfulness guarantee. This is the first setting in which it is known how to achieve nontrivial truthfulness guarantees for students when computing school optimal matchings, assuming worst- case preferences (for schools and students) in large markets.

cs.GT↗

arXiv2013

Optimal Provision-After-Wait in Healthcare

We investigate computational and mechanism design aspects of scarce resource allocation, where the primary rationing mechanism is through waiting times. Specifically we consider allocating medical treatments to a population of patients. Each patient needs exactly one treatment, and can choose from $k$ hospitals. Hospitals have different costs, which are fully paid by a third party ---the "payer". The payer has a fixed budget $B$, and each hospital will have its own waiting time. At equilibrium, each patient will choose his most preferred hospital given his intrinsic preferences and the waiting times. The payer thus computes the waiting times so that at equilibrium the budget constraint is satisfied and the social welfare is maximized. We first show that the optimization problem is NP-hard, yet if the budget can be relaxed to $(1+ε)B$ for an arbitrarily small $ε$, then the optimum under budget $B$ can be approximated efficiently. Next, we study the endogenous emergence of waiting time from the dynamics between hospitals and patients, and show that there is no need for the payer to explicitly enforce the optimal waiting times. Under certain conditions, all he need is to enforce the amount of money he wants to pay to each hospital. The dynamics will always converge to the desired waiting times in finite time. We then go beyond equilibrium solutions and investigate the optimization problem over a much larger class of mechanisms containing the equilibrium ones as special cases. With two hospitals, we show that under a natural assumption on the patients' preference profiles, optimal welfare is in fact attained by the randomized assignment mechanism, which allocates patients to hospitals at random subject to the budget constraint, but avoids waiting times. Finally, we discuss potential policy implications of our results, as well as follow-up directions and open problems.

cs.GT↗

arXiv2012

The Exponential Mechanism for Social Welfare: Private, Truthful, and Nearly Optimal

In this paper we show that for any mechanism design problem with the objective of maximizing social welfare, the exponential mechanism can be implemented as a truthful mechanism while still preserving differential privacy. Our instantiation of the exponential mechanism can be interpreted as a generalization of the VCG mechanism in the sense that the VCG mechanism is the extreme case when the privacy parameter goes to infinity. To our knowledge, this is the first general tool for designing mechanisms that are both truthful and differentially private.

cs.GT↗