
QueueChannel Capacities with Generalized Amplitude Damping
The generalized amplitude damping channel (GADC) is considered an import...
read it

Statistically Robust, RiskAverse Best Arm Identification in MultiArmed Bandits
Traditional multiarmed bandit (MAB) formulations usually make certain a...
read it

Bandit algorithms: Letting go of logarithmic regret for statistical robustness
We study regret minimization in a stochastic multiarmed bandit setting ...
read it

Constrained regret minimization for multicriterion multiarmed bandits
We consider a stochastic multiarmed bandit setting and study the proble...
read it

A Framework for EndtoEnd Deep LearningBased Anomaly Detection in Transportation Networks
We develop an endtoend deep learningbased anomaly detection model for...
read it

LSTMBased Anomaly Detection: Detection Rules from Extreme Value Theory
In this paper, we explore various statistical techniques for anomaly det...
read it

The Classical Capacity of a Quantum Erasure QueueChannel
We consider a setting where a stream of qubits is processed sequentially...
read it

Distribution oblivious, riskaware algorithms for multiarmed bandits with unbounded rewards
Classical multiarmed bandit problems use the expected value of an arm a...
read it

On Minimizing the Maximum AgeofInformation For Wireless Erasure Channels
AgeofInformation (AoI) is a recently proposed metric for quantifying t...
read it

Grids versus Graphs: Partitioning Space for Improved Taxi DemandSupply Forecasts
Accurate taxi demandsupply forecasting is a challenging application of ...
read it

Riskaware Multiarmed Bandits Using Conditional ValueatRisk
Traditional multiarmed bandit problems are geared towards finding the a...
read it

Taxi DemandSupply Forecasting: Impact of Spatial Partitioning on the Performance of Neural Networks
In this paper, we investigate the significance of choosing an appropriat...
read it

Concentration bounds for empirical conditional valueatrisk: The unbounded case
In several realworld applications involving decision making under uncer...
read it

Taxi demand forecasting: A HEDGE based tessellation strategy for improved accuracy
A key problem in locationbased modeling and forecasting lies in identif...
read it

Qubits through Queues: The Capacity of Channels with Waiting Time Dependent Errors
We consider a setting where qubits are processed sequentially, and deriv...
read it

Caching under Content Freshness Constraints
Several realtime delaysensitive applications pose varying degrees of f...
read it

Collaborative Learning of Stochastic Bandits over a Social Network
We consider a collaborative online learning paradigm, wherein a group of...
read it
Krishna Jagannathan
is this you? claim profile