1106 search results - page 8 / 222 » On regularization algorithms in learning theory |
130
Voted
SIGECOM
2010
ACM
15 years 8 months ago
2010
ACM
We explore the striking mathematical connections that exist between market scoring rules, cost function based prediction markets, and no-regret learning. We first show that any c...
151
click to vote
TCS
2008
15 years 3 months ago
2008
This paper studies a novel paradigm for learning formal languages from positive and negative examples which consists of mapping strings to an appropriate highdimensional feature s...
103
Voted
ICML
2010
IEEE
15 years 5 months ago
2010
IEEE
Optimization problems with a nuclear norm regularization, such as e.g. low norm matrix factorizations, have seen many applications recently. We propose a new approximation algorit...
132
Voted
ICML
2009
IEEE
16 years 4 months ago
2009
IEEE
Many learning algorithms rely on the curvature (in particular, strong convexity) of regularized objective functions to provide good theoretical performance guarantees. In practice...
142
click to vote
ICML
2009
IEEE
16 years 4 months ago
2009
IEEE
We consider the task of reinforcement learning with linear value function approximation. Temporal difference algorithms, and in particular the Least-Squares Temporal Difference (L...