We describe a new approach to default reasoning, based on a principle of indi erence among possible worlds. We interpret default rules as extreme statistical statements, thus obta...
Fahiem Bacchus, Adam J. Grove, Joseph Y. Halpern, ...
The most basic assumption used in statistical learning theory is that training data and test data are drawn from the same underlying distribution. Unfortunately, in many applicati...
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...
We put forth a new computational notion of entropy, which measures the (in)feasibility of sampling high entropy strings that are consistent with a given protocol. Specifically, we...
Iftach Haitner, Omer Reingold, Salil P. Vadhan, Ho...
The causal states of computational mechanics define the minimal sufficient (prescient) memory for a given stationary stochastic process. They induce the -machine which is a hidden...