Sciweavers

32 search results - page 5 / 7
» Bounding Performance Loss in Approximate MDP Homomorphisms
Sort
View
ECCV
2008
Springer
14 years 7 months ago
Efficiently Learning Random Fields for Stereo Vision with Sparse Message Passing
As richer models for stereo vision are constructed, there is a growing interest in learning model parameters. To estimate parameters in Markov Random Field (MRF) based stereo formu...
Jerod J. Weinman, Lam Tran, Christopher J. Pal
COLT
2005
Springer
13 years 10 months ago
Margin-Based Ranking Meets Boosting in the Middle
Abstract. We present several results related to ranking. We give a general margin-based bound for ranking based on the L∞ covering number of the hypothesis space. Our bound sugge...
Cynthia Rudin, Corinna Cortes, Mehryar Mohri, Robe...
JUCS
2007
98views more  JUCS 2007»
13 years 5 months ago
Focus of Attention in Reinforcement Learning
Abstract: Classification-based reinforcement learning (RL) methods have recently been proposed as an alternative to the traditional value-function based methods. These methods use...
Lihong Li, Vadim Bulitko, Russell Greiner
CISS
2008
IEEE
13 years 11 months ago
Rate adaptation via link-layer feedback for goodput maximization over a time-varying channel
Abstract—We consider adapting the transmission rate to maximize the goodput, i.e., the amount of data transmitted without error, over a continuous Markov flat-fading wireless ch...
Rohit Aggarwal, Phil Schniter, Can Emre Koksal
CORR
2010
Springer
121views Education» more  CORR 2010»
13 years 3 months ago
Mechanism Design via Correlation Gap
For revenue and welfare maximization in singledimensional Bayesian settings, Chawla et al. (STOC10) recently showed that sequential posted-price mechanisms (SPMs), though simple i...
Qiqi Yan