In this paper, we study the problem of learning the structure of Markov Networks that permit efficient inference. We formulate structure learning as an optimization problem that maximizes the likelihood of the model such that the inference complexity on the resulting structure is bounded. The inference complexity is measured with respect to any chosen algorithm (either exact or approximate), or...

In this paper, the artificial boundary method for Poisson problem in an infinite domain with a concave angle is investigated. The exact and approximate elliptical arc artificial boundary conditions are given. The finite element approximation is formulated in a bounded domain using the approximate artificial boundary condition and error estimates are obtained. Finally, some numerical examples sh...

Load Frequency Control (LFC) has received considerable attention during last decades. This paper proposes a new method for designing decentralized interaction estimators for interconnected large-scale systems and utilizes it to multi-area power systems. For each local area, a local estimator is designed to estimate the interactions of this area using only the local output measurements. In fact,...

This paper considers the stability of online learning algorithms and its implications for learnability (bounded regret). We introduce a novel quantity called forward regret that intuitively measures how good an online learning algorithm is if it is allowed a one-step look-ahead into the future. We show that given stability, bounded forward regret is equivalent to bounded regret. We also show th...

Denote by [0, ω1) the locally compact Hausdorff space consisting of all countable ordinals, equipped with the order topology, and let C0[0, ω1) be the Banach space of scalar-valued, continuous functions which are defined on [0, ω1) and vanish eventually. We show that a weak ∗compact subset of the dual space of C0[0, ω1) is either uniformly Eberlein compact, or it contains a homeomorphic copy of...