2
2.0
Jun 30, 2018
06/18
by
Qingqing Huang; Rong Ge; Sham Kakade; Munther Dahleh
texts
eye 2
favorite 0
comment 0
Consider a stationary discrete random process with alphabet size d, which is assumed to be the output process of an unknown stationary Hidden Markov Model (HMM). Given the joint probabilities of finite length strings of the process, we are interested in finding a finite state generative model to describe the entire process. In particular, we focus on two classes of models: HMMs and quasi-HMMs, which is a strictly larger class of models containing HMMs. In the main theorem, we show that if the...
Topics: Computing Research Repository, Learning
Source: http://arxiv.org/abs/1411.3698
2
2.0
Jun 29, 2018
06/18
by
Qingqing Huang; Sham M. Kakade; Weihao Kong; Gregory Valiant
texts
eye 2
favorite 0
comment 0
We consider the problem of accurately recovering a matrix B of size M by M , which represents a probability distribution over M2 outcomes, given access to an observed matrix of "counts" generated by taking independent samples from the distribution B. How can structural properties of the underlying matrix B be leveraged to yield computationally efficient and information theoretically optimal reconstruction algorithms? When can accurate reconstruction be accomplished in the sparse data...
Topics: Computing Research Repository, Learning
Source: http://arxiv.org/abs/1602.06586
9
9.0
Jun 28, 2018
06/18
by
Qingqing Huang; Sham M. Kakade
texts
eye 9
favorite 0
comment 0
Super-resolution is the problem of recovering a superposition of point sources using bandlimited measurements, which may be corrupted with noise. This signal processing problem arises in numerous imaging problems, ranging from astronomy to biology to spectroscopy, where it is common to take (coarse) Fourier measurements of an object. Of particular interest is in obtaining estimation procedures which are robust to noise, with the following desirable statistical and computational properties: we...
Topics: Computing Research Repository, Learning
Source: http://arxiv.org/abs/1509.07943
39
39
Sep 18, 2013
09/13
by
Qingqing Huang; Mardavij Roozbehani; Munther A Dahleh
texts
eye 39
favorite 0
comment 0
In this paper, we examine in an abstract framework, how a tradeoff between efficiency and robustness arises in different dynamic oligopolistic market architectures. We consider a market in which there is a monopolistic resource provider and agents that enter and exit the market following a random process. Self-interested and fully rational agents dynamically update their resource consumption decisions over a finite time horizon, under the constraint that the total resource consumption...
Source: http://arxiv.org/abs/1209.0229v2
7
7.0
Jun 27, 2018
06/18
by
Rong Ge; Qingqing Huang; Sham M. Kakade
texts
eye 7
favorite 0
comment 0
Efficiently learning mixture of Gaussians is a fundamental problem in statistics and learning theory. Given samples coming from a random one out of k Gaussian distributions in Rn, the learning problem asks to estimate the means and the covariance matrices of these Gaussians. This learning problem arises in many areas ranging from the natural sciences to the social sciences, and has also found many machine learning applications. Unfortunately, learning mixture of Gaussians is an information...
Topics: Learning, Computing Research Repository
Source: http://arxiv.org/abs/1503.00424
51
51
Sep 23, 2013
09/13
by
Ying Cui; Qingqing Huang; Vincent K. N. Lau
texts
eye 51
favorite 0
comment 0
In this paper, we propose a two-timescale delay-optimal dynamic clustering and power allocation design for downlink network MIMO systems. The dynamic clustering control is adaptive to the global queue state information (GQSI) only and computed at the base station controller (BSC) over a longer time scale. On the other hand, the power allocations of all the BSs in one cluster are adaptive to both intra-cluster channel state information (CCSI) and intra-cluster queue state information (CQSI), and...
Source: http://arxiv.org/abs/1012.3877v1
