JMLR
2012
12 years 2 months ago
2012
Many real-world problems are inherently hierarchically structured. The use of this structure in an agent’s policy may well be the key to improved scalability and higher performa...
EMNLP
2011
13 years 5 days ago
2011
We discuss and analyze the problem of finding a distribution that minimizes the relative entropy to a prior distribution while satisfying max-norm constraints with respect to an ...
CORR
2011
Springer
13 years 4 months ago
2011
Springer
This paper provides a succinct proof of a 1973 theorem of Lieb that establishes the concavity of a certain trace function. The development relies on a deep result from quantum info...
CCE
2011
13 years 7 months ago
2011
The robustness of a system is a property that pervades all aspects of Nature. The ability of a system to adapt itself to perturbations due to internal and external agents, to agin...
TIT
2010
13 years 7 months ago
2010
A random variable with distribution P is observed in Gaussian noise and is estimated by a minimum meansquare estimator that assumes that the distribution is Q. This paper shows tha...
CORR
2011
Springer
13 years 7 months ago
2011
Springer
Let X be a non-negative random variable and let the conditional distribution of a random variable Y , given X, be Poisson(γ · X), for a parameter γ ≥ 0. We identify a natural...
IJNSEC
2007
14 years 10 days ago
2007
In this paper, we propose a discrete cosine transform (DCT) based spread spectrum data-hiding algorithm that is resilient to statistical attacks. Unlike other spread spectrum base...
SSWMC
2004
14 years 1 months ago
2004
We study a detection-theoretic approach to steganalysis. The relative entropy between covertext and stegotext determines the steganalyzer's difficulty in discriminating them,...
COLT
2006
Springer
14 years 2 months ago
2006
Springer
There are two main families of on-line algorithms depending on whether a relative entropy or a squared Euclidean distance is used as a regularizer. The difference between the two f...
COLT
1995
Springer
14 years 4 months ago
1995
Springer
We investigate the problem of estimating the proportion vector which maximizes the likelihood of a given sample for a mixture of given densities. We adapt a framework developed for...