• Publications
  • Influence
Active Sequential Hypothesis Testing
TLDR
Lower bounds for the optimal total cost are established using results in dynamic programming and the fundamental limits on the maximum achievable information acquisition rate and the optimal reliability are characterized. Expand
Extrinsic Jensen–Shannon Divergence: Applications to Variable-Length Coding
TLDR
This paper presents strictly positive lower bounds on EJS divergence, and hence nonasymptotic upper bounds on the expected code length, for the following two coding schemes: 1) variable-length posterior matching and 2) MaxEJS coding scheme that is based on a greedy maximization of the E JS divergence. Expand
Optimal reliability over a class of binary-input channels with feedback
TLDR
A deterministic sequential coding scheme is proposed and shown to attain the optimal error exponent for any binary-input channel whose capacity is achieved by the uniform input distribution. Expand
Active M-ary sequential hypothesis testing
This paper considers a generalized sequential hypothesis testing problem in which a decision maker not only can sequentially trade off the sensing cost with the declaration precision, but also canExpand
Opportunistic Routing with Congestion Diversity in Wireless Multi-hop Networks
TLDR
This paper provides an opportunistic routing policy with congestion diversity (ORCD), a measure of draining time to opportunistically identify and route packets along the paths with an expected low overall congestion, and proposes practical implementations and discusses criticality of various aspects of the algorithm. Expand
An adaptive opportunistic routing scheme for wireless ad-hoc networks
TLDR
An adaptive opportunistic routing scheme for multi-hop wireless ad-hoc networks that utilizes a reinforcement learning framework to achieve the optimal performance even in the absence of reliable knowledge about channel statistics and network model is proposed. Expand
Extrinsic Jensen-Shannon divergence with application in active hypothesis testing
TLDR
Using EJS as an information utility, a heuristic policy for selecting actions is proposed and Via numerical and asymptotic optimality analysis, the performance of the proposed policy is investigated, hence the applicability of the EJS divergence in the context of the active hypothesis testing is investigated. Expand
Bayesian Active Learning With Non-Persistent Noise
TLDR
The sampling strategy is motivated by a connection between Bayesian active learning and active hypothesis testing, and is based on querying the label of a sample, which maximizes the extrinsic Jensen-Shannon divergence at each step. Expand
Sequentiality and Adaptivity Gains in Active Hypothesis Testing
TLDR
Performance bounds are provided for the policies in each category of sequentiality gain and adaptivity gain and the gains of sequential and adaptive selection of actions are characterized. Expand
Noisy Bayesian active learning
TLDR
Viewing the problem as an information acquisition problem enables a deterministic and Markov heuristic policy based on greedy maximization of Extrinsic Jensen-Shannon divergence and it is shown that this heuristic is better than previous results and matches the earlier proposed lower bound asymptotically. Expand
...
1
2
3
4
...