101
click to vote
AAAI
2015
10 years 1 months ago
2015
Current algorithms for the standard multi-armed bandit problem have good empirical performance and optimal regret bounds. However, real-world problems often differ from the standa...
AAAI
2015
10 years 1 months ago
2015
Is it possible to maximize a monotone submodular function faster than the widely used lazy greedy algorithm (also known as accelerated greedy), both in theory and practice? In thi...
AAAI
2015
10 years 1 months ago
2015
AAAI
2015
10 years 1 months ago
2015
We consider the problem of learning deep representation when target labels are available. In this paper, we show that there exists intrinsic relationship between target coding and...
119
click to vote
AAAI
2015
10 years 1 months ago
2015
In many real-world situations a decision maker may make decisions across many separate reinforcement learning tasks in parallel, yet there has been very little work on concurrent ...