arXiv subjects

Krishna Jagannathan

Publications and source records attributed to Krishna Jagannathan.

At least 37 records · Page 2Linked to original sources

arXiv2020

Bandit algorithms: Letting go of logarithmic regret for statistical robustness

We study regret minimization in a stochastic multi-armed bandit setting and establish a fundamental trade-off between the regret suffered under an algorithm, and its statistical robustness. Considering broad classes of underlying arms' distributions, we show that bandit learning algorithms with logarithmic regret are always inconsistent and that consistent learning algorithms always suffer a super-logarithmic regret. This result highlights the inevitable statistical fragility of all `logarithmic regret' bandit algorithms available in the literature---for instance, if a UCB algorithm designed for $σ$-subGaussian distributions is used in a subGaussian setting with a mismatched variance parameter, the learning performance could be inconsistent. Next, we show a positive result: statistically robust and consistent learning performance is attainable if we allow the regret to be slightly worse than logarithmic. Specifically, we propose three classes of distribution oblivious algorithms that achieve an asymptotic regret that is arbitrarily close to logarithmic.

cs.LG↗

arXiv2019

A Framework for End-to-End Deep Learning-Based Anomaly Detection in Transportation Networks

We develop an end-to-end deep learning-based anomaly detection model for temporal data in transportation networks. The proposed EVT-LSTM model is derived from the popular LSTM (Long Short-Term Memory) network and adopts an objective function that is based on fundamental results from EVT (Extreme Value Theory). We compare the EVT-LSTM model with some established statistical, machine learning, and hybrid deep learning baselines. Experiments on seven diverse real-world data sets demonstrate the superior anomaly detection performance of our proposed model over the other models considered in the comparison study.

cs.LG↗

arXiv2019

LSTM-Based Anomaly Detection: Detection Rules from Extreme Value Theory

In this paper, we explore various statistical techniques for anomaly detection in conjunction with the popular Long Short-Term Memory (LSTM) deep learning model for transportation networks. We obtain the prediction errors from an LSTM model, and then apply three statistical models based on (i) the Gaussian distribution, (ii) Extreme Value Theory (EVT), and (iii) the Tukey's method. Using statistical tests and numerical studies, we find strong evidence against the widely employed Gaussian distribution based detection rule on the prediction errors. Next, motivated by fundamental results from Extreme Value Theory, we propose a detection technique that does not assume any parent distribution on the prediction errors. Through numerical experiments conducted on several real-world traffic data sets, we show that the EVT-based detection rule is superior to other detection rules, and is supported by statistical evidence.

cs.LG↗

arXiv2019

Concentration bounds for CVaR estimation: The cases of light-tailed and heavy-tailed distributions

Conditional Value-at-Risk (CVaR) is a widely used risk metric in applications such as finance. We derive concentration bounds for CVaR estimates, considering separately the cases of light-tailed and heavy-tailed distributions. In the light-tailed case, we use a classical CVaR estimator based on the empirical distribution constructed from the samples. For heavy-tailed random variables, we assume a mild `bounded moment' condition, and derive a concentration bound for a truncation-based estimator. Notably, our concentration bounds enjoy an exponential decay in the sample size, for heavy-tailed as well as light-tailed distributions. To demonstrate the applicability of our concentration results, we consider a CVaR optimization problem in a multi-armed bandit setting. Specifically, we address the best CVaR-arm identification problem under a fixed budget. We modify the well-known successive rejects algorithm to incorporate a CVaR-based criterion. Using the CVaR concentration result, we derive an upper-bound on the probability of incorrect identification by the proposed algorithm.

cs.LG↗

arXiv2019

Distribution oblivious, risk-aware algorithms for multi-armed bandits with unbounded rewards

Classical multi-armed bandit problems use the expected value of an arm as a metric to evaluate its goodness. However, the expected value is a risk-neutral metric. In many applications like finance, one is interested in balancing the expected return of an arm (or portfolio) with the risk associated with that return. In this paper, we consider the problem of selecting the arm that optimizes a linear combination of the expected reward and the associated Conditional Value at Risk (CVaR) in a fixed budget best-arm identification framework. We allow the reward distributions to be unbounded or even heavy-tailed. For this problem, our goal is to devise algorithms that are entirely distribution oblivious, i.e., the algorithm is not aware of any information on the reward distributions, including bounds on the moments/tails, or the suboptimality gaps across arms. In this paper, we provide a class of such algorithms with provable upper bounds on the probability of incorrect identification. In the process, we develop a novel estimator for the CVaR of unbounded (including heavy-tailed) random variables and prove a concentration inequality for the same, which could be of independent interest. We also compare the error bounds for our distribution oblivious algorithms with those corresponding to standard non-oblivious algorithms. Finally, numerical experiments reveal that our algorithms perform competitively when compared with non-oblivious algorithms, suggesting that distribution obliviousness can be realised in practice without incurring a significant loss of performance.

cs.LG↗

arXiv2019

Qubits through Queues: The Capacity of Channels with Waiting Time Dependent Errors

We consider a setting where qubits are processed sequentially, and derive fundamental limits on the rate at which classical information can be transmitted using quantum states that decohere in time. Specifically, we model the sequential processing of qubits using a single server queue, and derive explicit expressions for the capacity of such a `queue-channel.' We also demonstrate a sweet-spot phenomenon with respect to the arrival rate to the queue, i.e., we show that there exists a value of the arrival rate of the qubits at which the rate of information transmission (in bits/sec) through the queue-channel is maximized. Next, we consider a setting where the average rate of processing qubits is fixed, and show that the capacity of the queue-channel is maximized when the processing time is deterministic. We also discuss design implications of these results on quantum information processing systems.

cs.IT↗

arXiv2019

On Minimizing the Maximum Age-of-Information For Wireless Erasure Channels

Age-of-Information (AoI) is a recently proposed metric for quantifying the freshness of information from the UE's perspective in a communication network. Recently, Kadota et al. [1] have proposed an index-type approximately optimal scheduling policy for minimizing the average-AoI metric for a downlink transmission problem. For delay-sensitive applications, including real-time control of a cyber-physical system, or scheduling URLLC traffic in 5G, it is essential to have a more stringent uniform control on AoI across all users. In this paper, we derive an exactly optimal scheduling policy for this problem in a downlink cellular system with erasure channels. Our proof of optimality involves an explicit solution to the associated average-cost Bellman Equation, which might be of independent theoretical interest. We also establish that the resulting Age-process is positive recurrent under the optimal policy, and has an exponentially light tail, with the optimal large-deviation exponent. Finally, motivated by typical applications in small-cell residential networks, we consider the problem of minimizing the peak-AoI with throughput constraints to specific UEs, and derive a heuristic policy for this problem. Extensive numerical simulations have been carried out to compare the efficacy of the proposed policies with other well-known scheduling policies, such as Randomized scheduling and Proportional Fair.

cs.IT↗

arXiv2019

Grids versus Graphs: Partitioning Space for Improved Taxi Demand-Supply Forecasts

Accurate taxi demand-supply forecasting is a challenging application of ITS (Intelligent Transportation Systems), due to the complex spatial and temporal patterns. We investigate the impact of different spatial partitioning techniques on the prediction performance of an LSTM (Long Short-Term Memory) network, in the context of taxi demand-supply forecasting. We consider two tessellation schemes: (i) the variable-sized Voronoi tessellation, and (ii) the fixed-sized Geohash tessellation. While the widely employed ConvLSTM (Convolutional LSTM) can model fixed-sized Geohash partitions, the standard convolutional filters cannot be applied on the variable-sized Voronoi partitions. To explore the Voronoi tessellation scheme, we propose the use of GraphLSTM (Graph-based LSTM), by representing the Voronoi spatial partitions as nodes on an arbitrarily structured graph. The GraphLSTM offers competitive performance against ConvLSTM, at lower computational complexity, across three real-world large-scale taxi demand-supply data sets, with different performance metrics. To ensure superior performance across diverse settings, a HEDGE based ensemble learning algorithm is applied over the ConvLSTM and the GraphLSTM networks.

cs.LG↗

arXiv2018

Right buffer sizing matters: some dynamical and statistical studies on Compound TCP

Motivated by recent concerns that queuing delays in the Internet are on the rise, we conduct a performance evaluation of Compound TCP (C-TCP) in two topologies: a single bottleneck and a multi-bottleneck topology, under different traffic scenarios. The first topology consists of a single bottleneck router, and the second consists of two distinct sets of TCP flows, regulated by two edge routers, feeding into a common core router. We focus on some dynamical and statistical properties of the underlying system. From a dynamical perspective, we develop fluid models in a regime wherein the number of flows is large, bandwidth-delay product is high, buffers are dimensioned small (independent of the bandwidth-delay product) and routers deploy a Drop-Tail queue policy. A detailed local stability analysis for these models yields the following key insight: smaller buffers favour stability. Additionally, we highlight that larger buffers, in addition to increasing latency, are prone to inducing limit cycles in the system dynamics, via a Hopf bifurcation. These limit cycles in turn cause synchronisation among the TCP flows, and also result in a loss of link utilisation. For the topologies considered, we also empirically analyse some statistical properties of the bottleneck queues. These statistical analyses serve to validate an important modelling assumption: that in the regime considered, each bottleneck queue may be approximated as either an $M/M/1/B$ or an $M/D/1/B$ queue. This immediately makes the modelling perspective attractive and the analysis tractable. Finally, we show that smaller buffers, in addition to ensuring stability and low latency, would also yield fairly good system performance, in terms of throughput and flow completion times.

cs.NI↗

arXiv2018

Taxi Demand-Supply Forecasting: Impact of Spatial Partitioning on the Performance of Neural Networks

In this paper, we investigate the significance of choosing an appropriate tessellation strategy for a spatio-temporal taxi demand-supply modeling framework. Our study compares (i) the variable-sized polygon based Voronoi tessellation, and (ii) the fixed-sized grid based Geohash tessellation, using taxi demand-supply GPS data for the cities of Bengaluru, India and New York, USA. Long Short-Term Memory (LSTM) networks are used for modeling and incorporating information from spatial neighbors into the model. We find that the LSTM model based on input features extracted from a variable-sized polygon tessellation yields superior performance over the LSTM model based on fixed-sized grid tessellation. Our study highlights the need to explore multiple spatial partitioning techniques for improving the prediction performance in neural network models.

cs.LG↗

arXiv2018

Concentration bounds for empirical conditional value-at-risk: The unbounded case

In several real-world applications involving decision making under uncertainty, the traditional expected value objective may not be suitable, as it may be necessary to control losses in the case of a rare but extreme event. Conditional Value-at-Risk (CVaR) is a popular risk measure for modeling the aforementioned objective. We consider the problem of estimating CVaR from i.i.d. samples of an unbounded random variable, which is either sub-Gaussian or sub-exponential. We derive a novel one-sided concentration bound for a natural sample-based CVaR estimator in this setting. Our bound relies on a concentration result for a quantile-based estimator for Value-at-Risk (VaR), which may be of independent interest.

cs.LG↗

arXiv2018

Taxi demand forecasting: A HEDGE based tessellation strategy for improved accuracy

A key problem in location-based modeling and forecasting lies in identifying suitable spatial and temporal resolutions. In particular, judicious spatial partitioning can play a significant role in enhancing the performance of location-based forecasting models. In this work, we investigate two widely used tessellation strategies for partitioning city space, in the context of real-time taxi demand forecasting. Our study compares (i) Geohash tessellation, and (ii) Voronoi tessellation, using two distinct taxi demand datasets, over multiple time scales. For the purpose of comparison, we employ classical time-series tools to model the spatio-temporal demand. Our study finds that the performance of each tessellation strategy is highly dependent on the city geography, spatial distribution of the data, and the time of the day, and that neither strategy is found to perform optimally across the forecast horizon. We propose a hybrid tessellation algorithm that picks the best tessellation strategy at each instant, based on their performance in the recent past. Our hybrid algorithm is a non-stationary variant of the well-known HEDGE algorithm for choosing the best advice from multiple experts. We show that the hybrid tessellation strategy performs consistently better than either of the two strategies across the data sets considered, at multiple time scales, and with different performance metrics. We achieve an average accuracy of above 80% per km^2 for both data sets considered at 60 minute aggregation levels.

cs.LG↗

arXiv2018

Impact of delayed acceleration feedback on the classical car-following model

Delayed feedback plays a vital role in determining the qualitative dynamical properties of a platoon of vehicles driving on a straight road. Motivated by the positive impact of Delayed Acceleration Feedback (DAF) in various scenarios, in this paper, we incorporate DAF into the Classical Car-Following Model (CCFM). We begin by deriving the Classical Car-Following Model with Delayed Acceleration Feedback (CCFM-DAF). We then derive the necessary and sufficient condition for local stability of the CCFM-DAF. Next, we show that the CCFM-DAF transits from the locally stable to the unstable regime via a Hopf bifurcation; thus leading to the emergence of limit cycles in system dynamics. We then propose a suitable linear transformation that enables us to analyze the local bifurcation properties of the CCFM-DAF by studying the analogous properties of the CCFM. We also study the impact of DAF on three important dynamical properties of the CCFM; namely, non-oscillatory convergence, string stability and robust stability. Our analyses are complemented with a stability chart and a bifurcation diagram. Our work reveals the following detrimental effects of DAF on the CCFM: (i) reduction in the locally stable region, (ii) increase in the frequency of the emergent limit cycles, (iii) decrease in the amplitude of the emergent limit cycles, (iv) destruction of the non-oscillatory property, (vi) increased risk of string instability, and (vii) reduced resilience towards parametric uncertainty. Thus, we report a practically-relevant application wherein DAF degrades the performance in several metrics of interest.

eess.SY↗

arXiv2018

Stability, convergence and Hopf bifurcation analyses of the classical car-following model

Reaction delays play an important role in determining the qualitative dynamical properties of a platoon of vehicles traversing a straight road. In this paper, we investigate the impact of delayed feedback on the dynamics of the Classical Car-Following Model (CCFM). Specifically, we analyze the CCFM in no delay, small delay and arbitrary delay regimes. First, we derive a sufficient condition for local stability of the CCFM in no-delay and small-delay regimes using. Next, we derive the necessary and sufficient condition for local stability of the CCFM for an arbitrary delay. We then demonstrate that the transition of traffic flow from the locally stable to the unstable regime occurs via a Hopf bifurcation, thus resulting in limit cycles in system dynamics. Physically, these limit cycles manifest as back-propagating congestion waves on highways. In the context of human-driven vehicles, our work provides phenomenological insight into the impact of reaction delays on the emergence and evolution of traffic congestion. In the context of self-driven vehicles, our work has the potential to provide design guidelines for control algorithms running in self-driven cars to avoid undesirable phenomena. Specifically, designing control algorithms that avoid jerky vehicular movements is essential. Hence, we derive the necessary and sufficient condition for non-oscillatory convergence of the CCFM. Next, we characterize the rate of convergence of the CCFM, and bring forth the interplay between local stability, non-oscillatory convergence and the rate of convergence of the CCFM. Further, to better understand the oscillations in the system dynamics, we characterize the type of the Hopf bifurcation and the asymptotic orbital stability of the limit cycles using Poincare normal forms and the center manifold theory. The analysis is complemented with stability charts, bifurcation diagrams and MATLAB simulations.

eess.SY↗

arXiv2017

Caching under Content Freshness Constraints

Several real-time delay-sensitive applications pose varying degrees of freshness demands on the requested content. The performance of cache replacement policies that are agnostic to these demands is likely to be sub-optimal. Motivated by this concern, in this paper, we study caching policies under a request arrival process which incorporates user freshness demands. We consider the performance metric to be the steady-state cache hit probability. We first provide a universal upper bound on the performance of any caching policy. We then analytically obtain the content-wise hit-rates for the Least Popular (LP) policy and provide sufficient conditions for the asymptotic optimality of cache performance under this policy. Next, we obtain an accurate approximation for the LRU hit-rates in the regime of large content population. To this end, we map the characteristic time of a content in the LRU policy to the classical Coupon Collector's Problem and show that it sharply concentrates around its mean. Further, we develop modified versions of these policies which eject cache redundancies present in the form of stale contents. Finally, we propose a new policy which outperforms the above policies by explicitly using freshness specifications of user requests to prioritize among the cached contents. We corroborate our analytical insights with extensive simulations.

cs.NI↗

arXiv2017

Congestion costs incurred on Indian Roads: A case study for New Delhi

We conduct a preliminary investigation into the levels of congestion in New Delhi, motivated by concerns due to rapidly growing vehicular congestion in Indian cities. First, we provide statistical evidence for the rising congestion levels on the roads of New Delhi from taxi GPS traces. Then, we estimate the economic costs of congestion in New Delhi. In particular, we estimate the marginal and the total costs of congestion. In calculating the marginal costs, we consider the following factors: (i) productivity loss, (ii) air pollution costs, and (iii) costs due to accidents. In calculating the total costs, in addition to the above factors, we also estimate the costs due to the wastage of fuel. We also project the associated costs due to productivity loss and air pollution till 2030. The projected traffic congestion costs for New Delhi comes around 14658 million US$/yr for the year 2030. The key takeaway from our current study is that costs due to productivity loss, particularly from buses, dominates the overall economic costs. Additionally, the expected increase in fuel wastage makes a strong case for intelligent traffic management systems.

physics.soc-ph↗

arXiv2017

The Modified Optimal Velocity Model: Stability Analyses and Design Guidelines

Reaction delays are important in determining the qualitative dynamical properties of a platoon of vehicles traveling on a straight road. In this paper, we investigate the impact of delayed feedback on the dynamics of the Modified Optimal Velocity Model (MOVM). Specifically, we analyze the MOVM in three regimes -- no delay, small delay and arbitrary delay. In the absence of reaction delays, we show that the MOVM is locally stable. For small delays, we then derive a sufficient condition for the MOVM to be locally stable. Next, for an arbitrary delay, we derive the necessary and sufficient condition for the local stability of the MOVM. We show that the traffic flow transits from the locally stable to the locally unstable regime via a Hopf bifurcation. We also derive the necessary and sufficient condition for non-oscillatory convergence and characterize the rate of convergence of the MOVM. These conditions help ensure smooth traffic flow, good ride quality and quick equilibration to the uniform flow. Further, since a Hopf bifurcation results in the emergence of limit cycles, we provide an analytical framework to characterize the type of the Hopf bifurcation and the asymptotic orbital stability of the resulting non-linear oscillations. Finally, we corroborate our analyses using stability charts, bifurcation diagrams, numerical computations and simulations conducted using MATLAB.

eess.SY↗

arXiv2017

Adaptive CSMA under the SINR Model: Efficient Approximation Algorithms for Throughput and Utility Maximization

We consider a Carrier Sense Multiple Access (CSMA) based scheduling algorithm for a single-hop wireless network under a realistic Signal-to-interference-plus-noise ratio (SINR) model for the interference. We propose two local optimization based approximation algorithms to efficiently estimate certain attempt rate parameters of CSMA called fugacities. It is known that adaptive CSMA can achieve throughput optimality by sampling feasible schedules from a Gibbs distribution, with appropriate fugacities. Unfortunately, obtaining these optimal fugacities is an NP-hard problem. Further, the existing adaptive CSMA algorithms use a stochastic gradient descent based method, which usually entails an impractically slow (exponential in the size of the network) convergence to the optimal fugacities. To address this issue, we first propose an algorithm to estimate the fugacities, that can support a given set of desired service rates. The convergence rate and the complexity of this algorithm are independent of the network size, and depend only on the neighborhood size of a link. Further, we show that the proposed algorithm corresponds exactly to performing the well-known Bethe approximation to the underlying Gibbs distribution. Then, we propose another local algorithm to estimate the optimal fugacities under a utility maximization framework, and characterize its accuracy. Numerical results indicate that the proposed methods have a good degree of accuracy, and achieve extremely fast convergence to near-optimal fugacities, and often outperform the convergence rate of the stochastic gradient descent by a few orders of magnitude.

cs.IT↗