Sciweavers

539 search results - page 6 / 108
» Learning Monotonic Linear Functions
Sort
View
IJCAI
2007
13 years 9 months ago
Learning from Partial Observations
We present a general machine learning framework for modelling the phenomenon of missing information in data. We propose a masking process model to capture the stochastic nature of...
Loizos Michael
AAAI
1990
13 years 8 months ago
Obtaining Quantitative Predictions from Monotone Relationships
: Tasks such as forecasting, diagnosis, and planning frequently require quantitative predictions . Typically, quantitative predictions are obtained by characterizing a system in te...
Joseph L. Hellerstein
ICML
2005
IEEE
14 years 8 months ago
Bounded real-time dynamic programming: RTDP with monotone upper bounds and performance guarantees
MDPs are an attractive formalization for planning, but realistic problems often have intractably large state spaces. When we only need a partial policy to get from a fixed start s...
H. Brendan McMahan, Maxim Likhachev, Geoffrey J. G...
CORR
2010
Springer
98views Education» more  CORR 2010»
13 years 7 months ago
Structure-Aware Stochastic Control for Transmission Scheduling
In this report, we consider the problem of real-time transmission scheduling over time-varying channels. We first formulate the transmission scheduling problem as a Markov decisio...
Fangwen Fu, Mihaela van der Schaar
MOR
2008
98views more  MOR 2008»
13 years 7 months ago
An Analysis of Monotone Follower Problems for Diffusion Processes
We consider a singular stochastic control problem, which is called the Monotone Follower Stochastic Control Problem and give sufficient conditions for the existence and uniqueness...
Erhan Bayraktar, Masahiko Egami