Sciweavers

4007 search results - page 247 / 802
» Computation with imprecise probabilities
Sort
View
NIPS
2007
15 years 5 months ago
Optimistic Linear Programming gives Logarithmic Regret for Irreducible MDPs
We present an algorithm called Optimistic Linear Programming (OLP) for learning to optimize average reward in an irreducible but otherwise unknown Markov decision process (MDP). O...
Ambuj Tewari, Peter L. Bartlett
UAI
2004
15 years 5 months ago
Monotonicity in Bayesian Networks
For many real-life Bayesian networks, common knowledge dictates that the output established for the main variable of interest increases with higher values for the observable varia...
Linda C. van der Gaag, Hans L. Bodlaender, A. J. F...
WSC
2001
15 years 5 months ago
Accounting for input model and parameter uncertainty in simulation
Taking into account input-model, input-parameter, and stochastic uncertainties inherent in many simulations, our Bayesian approach to input modeling yields valid point and confide...
Faker Zouaoui, James R. Wilson
AAAI
1996
15 years 5 months ago
A Clinician's Tool for Analyzing Non-Compliance
We describe a computer program to assist a clinician with assessing the e cacy of treatments in experimental studies for which treatment assignment is random but subject complianc...
David Maxwell Chickering, Judea Pearl
ICML
2010
IEEE
15 years 5 months ago
Restricted Boltzmann Machines are Hard to Approximately Evaluate or Simulate
Restricted Boltzmann Machines (RBMs) are a type of probability model over the Boolean cube {-1, 1}n that have recently received much attention. We establish the intractability of ...
Philip M. Long, Rocco A. Servedio