• Publications
  • Influence
Distributed Stochastic Subgradient Projection Algorithms for Convex Optimization
TLDR
This paper considers a distributed multi-agent network system where the goal is to minimize a sum of convex objective functions of the agents subject to a common convex constraint set, and investigates the effects of stochastic subgradient errors on the convergence of the algorithm.
General Asymptotic Bayesian Theory of Quickest Change Detection
TLDR
This paper investigates the performance of the Shiryaev procedure for general discrete-time stochastic models in the asymptotic setting, where the false alarm probability approaches zero and shows that the Shiryev procedure is asymPTotically optimal in the general non-i.i.d.\ case under mild conditions.
Gaussian Interference Networks: Sum Capacity in the Low-Interference Regime and New Outer Bounds on the Capacity Region
TLDR
New, improved outer bounds on the capacity region are developed and it is shown that treating interference as noise achieves the sum capacity of the two-user Gaussian interference channel in a low-interference regime, where the interference parameters are below certain thresholds.
A sequential procedure for multihypothesis testing
TLDR
The sequential testing of more than two hypotheses has important applications in direct-sequence spread spectrum signal acquisition, multiple-resolution-element radar, and other areas and it is argued that the MSPRT approximates the much more complicated optimal test when error probabilities are small and expected stopping times are large.
Tightening Mutual Information Based Bounds on Generalization Error
TLDR
Application to noisy and iterative algorithms, e.g., stochastic gradient Langevin dynamics (SGLD), is also studied, where the constructed bound provides a tighter characterization of the generalization error than existing results.
Cooperative Sensing for Primary Detection in Cognitive Radio
TLDR
This work designs a linear-quadratic (LQ) fusion strategy based on a deflection criterion for this problem, which takes into account the correlation between the nodes and shows that when the observations at the sensors are correlated, the LQ detector significantly outperforms the counting rule.
Decentralized detection in sensor networks
TLDR
A binary decentralized detection problem in which a network of wireless sensors provides relevant information about the state of nature to a fusion center, and it is shown that having a set of identical binary sensors is asymptotically optimal, as the number of observations per sensor goes to infinity.
Incremental Stochastic Subgradient Algorithms for Convex Optimization
TLDR
Convergence results and error bounds for the Markov randomized method in the presence of stochastic errors for diminishing and constant step-sizes are obtained.
Resource Allocation for Wireless Fading Relay Channels: Max-Min Solution
TLDR
Capacities are established for fading relay channels that satisfy certain conditions and lower and upper bounds on the capacity are derived, and are shown to match, and thus establish the capacity for the parallel relay channel with degraded subchannels.
Quickest Change Detection
...
...