arXiv subjects

Bhaskar Krishnamachari

Publications and source records attributed to Bhaskar Krishnamachari.

139 records · Page 8Linked to original sources

arXiv2011

The Non-Bayesian Restless Multi-Armed Bandit: A Case of Near-Logarithmic Strict Regret

In the classic Bayesian restless multi-armed bandit (RMAB) problem, there are $N$ arms, with rewards on all arms evolving at each time as Markov chains with known parameters. A player seeks to activate $K \geq 1$ arms at each time in order to maximize the expected total reward obtained over multiple plays. RMAB is a challenging problem that is known to be PSPACE-hard in general. We consider in this work the even harder non-Bayesian RMAB, in which the parameters of the Markov chain are assumed to be unknown \emph{a priori}. We develop an original approach to this problem that is applicable when the corresponding Bayesian problem has the structure that, depending on the known parameter values, the optimal solution is one of a prescribed finite set of policies. In such settings, we propose to learn the optimal policy for the non-Bayesian RMAB by employing a suitable meta-policy which treats each policy from this finite set as an arm in a different non-Bayesian multi-armed bandit problem for which a single-arm selection policy is optimal. We demonstrate this approach by developing a novel sensing policy for opportunistic spectrum access over unknown dynamic channels. We prove that our policy achieves near-logarithmic regret (the difference in expected reward compared to a model-aware genie), which leads to the same average reward that can be achieved by the optimal policy under a known model. This is the first such result in the literature for a non-Bayesian RMAB. For our proof, we also develop a novel generalization of the Chernoff-Hoeffding bound.

math.OC↗

arXiv2011

Efficient Online Learning for Opportunistic Spectrum Access

The problem of opportunistic spectrum access in cognitive radio networks has been recently formulated as a non-Bayesian restless multi-armed bandit problem. In this problem, there are N arms (corresponding to channels) and one player (corresponding to a secondary user). The state of each arm evolves as a finite-state Markov chain with unknown parameters. At each time slot, the player can select K < N arms to play and receives state-dependent rewards (corresponding to the throughput obtained given the activity of primary users). The objective is to maximize the expected total rewards (i.e., total throughput) obtained over multiple plays. The performance of an algorithm for such a multi-armed bandit problem is measured in terms of regret, defined as the difference in expected reward compared to a model-aware genie who always plays the best K arms. In this paper, we propose a new continuous exploration and exploitation (CEE) algorithm for this problem. When no information is available about the dynamics of the arms, CEE is the first algorithm to guarantee near-logarithmic regret uniformly over time. When some bounds corresponding to the stationary state distributions and the state-dependent rewards are known, we show that CEE can be easily modified to achieve logarithmic regret over time. In contrast, prior algorithms require additional information concerning bounds on the second eigenvalues of the transition matrices in order to guarantee logarithmic regret. Finally, we show through numerical simulations that CEE is more efficient than prior algorithms.

cs.LG↗

arXiv2011

Backpressure with Adaptive Redundancy (BWAR)

Backpressure scheduling and routing, in which packets are preferentially transmitted over links with high queue differentials, offers the promise of throughput-optimal operation for a wide range of communication networks. However, when the traffic load is low, due to the corresponding low queue occupancy, backpressure scheduling/routing experiences long delays. This is particularly of concern in intermittent encounter-based mobile networks which are already delay-limited due to the sparse and highly dynamic network connectivity. While state of the art mechanisms for such networks have proposed the use of redundant transmissions to improve delay, they do not work well when the traffic load is high. We propose in this paper a novel hybrid approach that we refer to as backpressure with adaptive redundancy (BWAR), which provides the best of both worlds. This approach is highly robust and distributed and does not require any prior knowledge of network load conditions. We evaluate BWAR through both mathematical analysis and simulations based on cell-partitioned model. We prove theoretically that BWAR does not perform worse than traditional backpressure in terms of the maximum throughput, while yielding a better delay bound. The simulations confirm that BWAR outperforms traditional backpressure at low load, while outperforming a state of the art encounter-routing scheme (Spray and Wait) at high load.

cs.NI↗

arXiv2011

A Packet Dropping Mechanism for Efficient Operation of M/M/1 Queues with Selfish Users

We consider a fundamental game theoretic problem concerning selfish users contributing packets to an M/M/1 queue. In this game, each user controls its own input rate so as to optimize a desired tradeoff between throughput and delay. We first show that the original game has an inefficient Nash Equilibrium (NE), with a Price of Anarchy (PoA) that scales linearly or worse in the number of users. In order to improve the outcome efficiency, we propose an easily implementable mechanism design whereby the server randomly drops packets with a probability that is a function of the total arrival rate. We show that this results in a modified M/M/1 queueing game that is an ordinal potential game with at least one NE. In particular, for a linear packet dropping function, which is similar to the Random Early Detection (RED) algorithm used in Internet Congestion Control, we prove that there is a unique NE. We also show that the simple best response dynamic converges to this unique equilibrium. Finally, for this scheme, we prove that the social welfare (expressed either as the summation of utilities of all players, or as the summation of the logarithm of utilities of all players) at the equilibrium point can be arbitrarily close to the social welfare at the global optimal point, i.e. the PoA can be made arbitrarily close to 1. We also study the impact of arrival rate estimation error on the PoA through simulations.

cs.GT↗

arXiv2011

LIFO-Backpressure Achieves Near Optimal Utility-Delay Tradeoff

There has been considerable recent work developing a new stochastic network utility maximization framework using Backpressure algorithms, also known as MaxWeight. A key open problem has been the development of utility-optimal algorithms that are also delay efficient. In this paper, we show that the Backpressure algorithm, when combined with the LIFO queueing discipline (called LIFO-Backpressure), is able to achieve a utility that is within $O(1/V)$ of the optimal value, while maintaining an average delay of $O([\log(V)]^2)$ for all but a tiny fraction of the network traffic. This result holds for general stochastic network optimization problems and general Markovian dynamics. Remarkably, the performance of LIFO-Backpressure can be achieved by simply changing the queueing discipline; it requires no other modifications of the original Backpressure algorithm. We validate the results through empirical measurements from a sensor network testbed, which show good match between theory and practice.

math.OC↗

arXiv2011

Decentralized Online Learning Algorithms for Opportunistic Spectrum Access

The fundamental problem of multiple secondary users contending for opportunistic spectrum access over multiple channels in cognitive radio networks has been formulated recently as a decentralized multi-armed bandit (D-MAB) problem. In a D-MAB problem there are $M$ users and $N$ arms (channels) that each offer i.i.d. stochastic rewards with unknown means so long as they are accessed without collision. The goal is to design a decentralized online learning policy that incurs minimal regret, defined as the difference between the total expected rewards accumulated by a model-aware genie, and that obtained by all users applying the policy. We make two contributions in this paper. First, we consider the setting where the users have a prioritized ranking, such that it is desired for the $K$-th-ranked user to learn to access the arm offering the $K$-th highest mean reward. For this problem, we present the first distributed policy that yields regret that is uniformly logarithmic over time without requiring any prior assumption about the mean rewards. Second, we consider the case when a fair access policy is required, i.e., it is desired for all users to experience the same mean reward. For this problem, we present a distributed policy that yields order-optimal regret scaling with respect to the number of users and arms, better than previously proposed policies in the literature. Both of our distributed policies make use of an innovative modification of the well known UCB1 policy for the classic multi-armed bandit problem that allows a single user to learn how to play the arm that yields the $K$-th largest mean reward.

cs.LG↗

arXiv2011

On the Combinatorial Multi-Armed Bandit Problem with Markovian Rewards

We consider a combinatorial generalization of the classical multi-armed bandit problem that is defined as follows. There is a given bipartite graph of $M$ users and $N \geq M$ resources. For each user-resource pair $(i,j)$, there is an associated state that evolves as an aperiodic irreducible finite-state Markov chain with unknown parameters, with transitions occurring each time the particular user $i$ is allocated resource $j$. The user $i$ receives a reward that depends on the corresponding state each time it is allocated the resource $j$. The system objective is to learn the best matching of users to resources so that the long-term sum of the rewards received by all users is maximized. This corresponds to minimizing regret, defined here as the gap between the expected total reward that can be obtained by the best-possible static matching and the expected total reward that can be achieved by a given algorithm. We present a polynomial-storage and polynomial-complexity-per-step matching-learning algorithm for this problem. We show that this algorithm can achieve a regret that is uniformly arbitrarily close to logarithmic in time and polynomial in the number of users and resources. This formulation is broadly applicable to scheduling and switching problems in networks and significantly extends prior results in the area.

math.OC↗

arXiv2010

Combinatorial Network Optimization with Unknown Variables: Multi-Armed Bandits with Linear Rewards

In the classic multi-armed bandits problem, the goal is to have a policy for dynamically operating arms that each yield stochastic rewards with unknown means. The key metric of interest is regret, defined as the gap between the expected total reward accumulated by an omniscient player that knows the reward means for each arm, and the expected total reward accumulated by the given policy. The policies presented in prior work have storage, computation and regret all growing linearly with the number of arms, which is not scalable when the number of arms is large. We consider in this work a broad class of multi-armed bandits with dependent arms that yield rewards as a linear combination of a set of unknown parameters. For this general framework, we present efficient policies that are shown to achieve regret that grows logarithmically with time, and polynomially in the number of unknown parameters (even though the number of dependent arms may grow exponentially). Furthermore, these policies only require storage that grows linearly in the number of unknown parameters. We show that this generalization is broadly applicable and useful for many interesting tasks in networks that can be formulated as tractable combinatorial optimization problems with linear objective functions, such as maximum weight matching, shortest path, and minimum spanning tree computations.

math.OC↗

arXiv2010

The Non-Bayesian Restless Multi-Armed Bandit: a Case of Near-Logarithmic Regret

math.OC↗

arXiv2009

Optimality of Myopic Sensing in Multi-Channel Opportunistic Access

We consider opportunistic communications over multiple channels where the state ("good" or "bad") of each channel evolves as independent and identically distributed Markov processes. A user, with limited sensing and access capability, chooses one channel to sense and subsequently access (based on the sensed channel state) in each time slot. A reward is obtained when the user senses and accesses a "good" channel. The objective is to design the optimal channel selection policy that maximizes the expected reward accrued over time. This problem can be generally cast as a Partially Observable Markov Decision Process (POMDP) or a restless multi-armed bandit process, to which optimal solutions are often intractable. We show in this paper that the myopic policy, with a simple and robust structure, achieves optimality under certain conditions. This result finds applications in opportunistic communications in fading environment, cognitive radio networks for spectrum overlay, and resource-constrained jamming and anti-jamming.

cs.NI↗

arXiv2008

Structure and Optimality of Myopic Policy in Opportunistic Access with Noisy Observations

A restless multi-armed bandit problem that arises in multichannel opportunistic communications is considered, where channels are modeled as independent and identical Gilbert-Elliot channels and channel state observations are subject to errors. A simple structure of the myopic policy is established under a certain condition on the false alarm probability of the channel state detector. It is shown that the myopic policy has a semi-universal structure that reduces channel selection to a simple round-robin procedure and obviates the need to know the underlying Markov transition probabilities. The optimality of the myopic policy is proved for the case of two channels and conjectured for the general case based on numerical examples.

cs.NI↗

arXiv2008

On Myopic Sensing for Multi-Channel Opportunistic Access: Structure, Optimality, and Performance

We consider a multi-channel opportunistic communication system where the states of these channels evolve as independent and statistically identical Markov chains (the Gilbert-Elliot channel model). A user chooses one channel to sense and access in each slot and collects a reward determined by the state of the chosen channel. The problem is to design a sensing policy for channel selection to maximize the average reward, which can be formulated as a multi-arm restless bandit process. In this paper, we study the structure, optimality, and performance of the myopic sensing policy. We show that the myopic sensing policy has a simple robust structure that reduces channel selection to a round-robin procedure and obviates the need for knowing the channel transition probabilities. The optimality of this simple policy is established for the two-channel case and conjectured for the general case based on numerical results. The performance of the myopic sensing policy is analyzed, which, based on the optimality of myopic sensing, characterizes the maximum throughput of a multi-channel opportunistic communication system and its scaling behavior with respect to the number of channels. These results apply to cognitive radio networks, opportunistic transmission in fading environments, and resource-constrained jamming and anti-jamming.

cs.NI↗

arXiv2006

Monotone properties of random geometric graphs have sharp thresholds

Random geometric graphs result from taking $n$ uniformly distributed points in the unit cube, $[0,1]^d$, and connecting two points if their Euclidean distance is at most $r$, for some prescribed $r$. We show that monotone properties for this class of graphs have sharp thresholds by reducing the problem to bounding the bottleneck matching on two sets of $n$ points distributed uniformly in $[0,1]^d$. We present upper bounds on the threshold width, and show that our bound is sharp for $d=1$ and at most a sublogarithmic factor away for $d\ge2$. Interestingly, the threshold width is much sharper for random geometric graphs than for Bernoulli random graphs. Further, a random geometric graph is shown to be a subgraph, with high probability, of another independently drawn random geometric graph with a slightly larger radius; this property is shown to have no analogue for Bernoulli random graphs.

math.PR↗