Learn More
Femtocells deployed in the Macrocell to improve the indoor coverage share the same spectrum with the Macrocells. The dynamic spectrum access (DSA) and power allocation (PA) for the users of Femtocells and Macrocells has an important influence on the mutual interference and system performance in Femtocell networks. In this paper, the DSA and PA problem is(More)
Recurrent neural networks (RNNs) have shown promising performance for language modeling. However, traditional training of RNNs, using back-propagation through time, often suffers from overfitting. One reason for this is that stochastic optimization (used for large training sets) does not provide good estimates of model uncertainty. This paper leverages(More)
In order to compute the marginal probability density function (PDF) with Gaussian belief propagation (BP), it is important to know whether it will converge in advance. By describing the message-passing process of Gaussian BP on the pairwise factor graph as a set of updating functions, the necessary and sufficient convergence condition of beliefs in(More)
We introduce the truncated Gaussian graphical model (TGGM) as a novel framework for designing statistical models for nonlinear learning. A TGGM is a Gaussian graphical model (GGM) with a subset of variables truncated to be nonnegative. The truncated variables are assumed latent and integrated out to induce a marginal model. We show that the variables in the(More)
It is known that Gaussian belief propagation (BP) is a low-complexity algorithm for (approximately) computing the marginal distribution of a high dimensional Gaussian distribution. However, in loopy factor graph, it is important to determine whether Gaussian BP converges. In general, the convergence conditions for Gaussian BP variances and means are not(More)
Gaussian graphical models (GGMs) are widely used for statistical modeling, because of ease of inference and the ubiquitous use of the normal distribution in practical approximations. However, they are also known for their limited modeling abilities, due to the Gaussian assumption. In this paper, we introduce a novel variant of GGMs, which relaxes the(More)
Belief propagation (BP) is an efficient algorithm for calculating approximate marginal probability density function (PDF) in large-scale Gaussian graphical models. It is known that when BP converges, the mean calculated by BP is the exact mean of the marginal PDF, while the accuracy of the variance calculated by BP is in general poor and unpredictable. In(More)
A macrocell superposed by indoor deployed femtocells forms a geography-overlapped and spectrum-shared two-tier network, which can efficiently improve coverage and enhance system capacity. To reduce inter-tier co-channel interference, femtocell user should choose suitable access channel according to the path losses between itself and the macrocell users.(More)
In order to compute the marginal distribution from a high dimensional distribution with loopy Gaussian belief propagation (BP), it is important to determine whether Gaussian BP would converge. In general, the convergence condition for Gaussian BP variance and mean are not necessarily the same, and this paper focuses on the convergence condition of Gaussian(More)
A latent-variable model is introduced for text matching, inferring sentence representations by jointly optimizing generative and discriminative objectives. To alleviate typical optimization challenges in latent-variable models for text, we employ deconvolutional networks as the sequence decoder (generator), providing learned latent codes with more semantic(More)