Learn More
We consider the problem of !nding a linear iteration that yields distributed averaging consensus over a network, i.e., that asymptotically computes the average of some initial values given at the nodes. When the iteration is assumed symmetric, the problem of !nding the fastest converging linear iteration can be cast as a semide!nite program, and therefore(More)
We consider a network of distributed sensors, where each sensor takes a linear measurement of some unknown parameters, corrupted by independent Gaussian noises. We propose a simple distributed iterative scheme, based on distributed average consensus in the network, to compute the maximum-likelihood estimate of the parameters. This scheme doesn't involve(More)
  • Lin Xiao
  • Journal of Machine Learning Research
  • 2010
We consider regularized stochastic learning and online optimization problems, where the objective function is the sum of two convex terms: one is the loss function of the learning task, and the other is a simple regularization term such as !1-norm for promoting sparsity. We develop extensions of Nesterov’s dual averaging method, that can exploit the(More)
We consider the problem of minimizing the sum of two convex functions: one is the average of a large number of smooth component functions, and the other is a general convex function that admits a simple proximal mapping. We assume the whole objective function is strongly convex. Such problems often arise in machine learning, known as regularized empirical(More)
Energy consumption in hosting Internet services is becoming a pressing issue as these services scale up. Dynamic server provisioning techniques are effective in turning off unnecessary servers to save energy. Such techniques, mostly studied for request-response services, face challenges in the context of connection servers that host a large number of(More)
Acetylation of proteins on lysine residues is a dynamic posttranslational modification that is known to play a key role in regulating transcription and other DNA-dependent nuclear processes. However, the extent of this modification in diverse cellular proteins remains largely unknown, presenting a major bottleneck for lysine-acetylation biology. Here we(More)
We consider a symmetric random walk on a connected graph, where each edge is labeled with the probability of transition between the two adjacent vertices. The associated Markov chain has a uniform equilibrium distribution; the rate of convergence to this distribution, i.e., the mixing rate of the Markov chain, is determined by the second largest (in(More)
In wireless networks, the optimal routing and resource allocation problems are coupled together through link capacities, which influence data routing and are determined by resource (e.g., power and bandwidth) allocation. We formulate the problem of simultaneous routing and resource allocation for wireless data networks as a convex optimization problem and(More)
Online prediction methods are typically presented as serial algorithms running on a single processor. However, in the age of web-scale prediction problems, it is increasingly common to encounter situations where a single processor cannot keep up with the high rate at which inputs arrive. In this work, we present the distributed mini-batch algorithm, a(More)
Bandit convex optimization is a special case of online convex optimization with partial information. In this setting, a player attempts to minimize a sequence of adversarially generated convex loss functions, while only observing the value of each function at a single point. In some cases, the minimax regret of these problems is known to be strictly worse(More)