
Bandit Quickest Changepoint Detection
Detecting abrupt changes in temporal behavior patterns is of interest in...
read it

Better than the Best: Gradientbased Improper Reinforcement Learning for Network Scheduling
We consider the problem of scheduling in constrained queueing networks w...
read it

Improper Learning with Gradientbased Policy Optimization
We consider an improper reinforcement learning setting where the learner...
read it

Stochastic Linear Bandits with Protected Subspace
We study a variant of the stochastic linear bandit problem wherein we op...
read it

Noregret Algorithms for Multitask Bayesian Optimization
We consider multiobjective optimization (MOO) of an unknown vectorvalu...
read it

Sequential Multihypothesis Testing in Multiarmed Bandit Problems:An Approach for Asymptotic Optimality
We consider a multihypothesis testing problem involving a Karmed bandi...
read it

Explicit Best Arm Identification in Linear Bandits Using NoRegret Learners
We study the problem of best arm identification in linearly parameterise...
read it

How Reliable are Test Numbers for Revealing the COVID19 Ground Truth and Applying Interventions?
The number of confirmed cases of COVID19 is often used as a proxy for t...
read it

Regret Minimization in Stochastic Contextual Dueling Bandits
We consider the problem of stochastic Karmed dueling bandit in the cont...
read it

Throughput Optimal Decentralized Scheduling with Singlebit State Feedback for a Class of Queueing Systems
Motivated by medium access control for resourcechallenged wireless Inte...
read it

Bestitem Learning in Random Utility Models with Subset Choices
We consider the problem of PAC learning the most valuable item from a po...
read it

Stability and Scalability of Blockchain Systems
The blockchain paradigm provides a mechanism for content dissemination a...
read it

Sequential Mode Estimation with Oracle Queries
We consider the problem of adaptively PAClearning a probability distrib...
read it

Towards Optimal and Efficient Best Arm Identification in Linear Bandits
We give a new algorithm for best arm identification in linearly paramete...
read it

On Online Learning in Kernelized Markov Decision Processes
We develop algorithms with low regret for learning episodic Markov decis...
read it

On Batch Bayesian Optimization
We present two algorithms for Bayesian optimization in the batch feedbac...
read it

On Adaptivity in Informationconstrained Online Learning
We study how to adapt to smoothlyvarying (`easy') environments in well...
read it

Bayesian Optimization under Heavytailed Payoffs
We consider black box optimization of an unknown function in the nonpara...
read it

From PAC to InstanceOptimal Sample Complexity in the PlackettLuce Model
We consider PAC learning for identifying a good item from subsetwise sa...
read it

Regret Minimisation in Multinomial Logit Bandits
We consider two regret minimisation problems over subsets of a finite gr...
read it

Active Ranking with Subsetwise Preferences
We consider the problem of probably approximately correct (PAC) ranking ...
read it

PACBattling Bandits with PlackettLuce: Tradeoff between Sample Complexity and Subset Size
We introduce the probably approximately correct (PAC) version of the pro...
read it

Online Learning in Kernelized Markov Decision Processes
We consider online learning for minimizing regret in unknown, episodic M...
read it

Optimal Odd Arm Identification with Fixed Confidence
The problem of detecting an odd arm from a set of K arms of a multiarme...
read it

Collaborative Learning of Stochastic Bandits over a Social Network
We consider a collaborative online learning paradigm, wherein a group of...
read it

Thompson Sampling for Learning Parameterized Markov Decision Processes
We consider reinforcement learning in parameterized Markov Decision Proc...
read it
Aditya Gopalan
is this you? claim profile