Negative Results for Active Learning with Convex Losses

12 years 11 months ago

Download www.cs.cmu.edu

We study the problem of active learning with convex loss functions. We prove that even under bounded noise constraints, the minimax rates for proper active learning are often no better than passive learning.

Steve Hanneke, Liu Yang

Real-time Traffic

Convex Loss Functions | JMLR 2010 | Passive Learning | Proper Active Learning |

claim paper

» Learning NonNegative Sparse Image Codes by Convex Programming

» Consistency of Multiclass Empirical Risk Minimization Methods Based on Convex Loss

» Optimizing estimated loss reduction for active sampling in rank learning

» Active Learning of Equivalence Relations by Minimizing the Expected Loss Using Constraint ...

» Sparseness Versus Estimating Conditional Probabilities Some Asymptotic Results

» Surrogate regret bounds for proper losses

» Learning Efficiently with Approximate Inference via Dual Losses

» Maximum Likelihood in CostSensitive Learning Model Specification Approximations and Upper ...

Post Info
More Details (n/a)

Added	19 May 2011
Updated	19 May 2011
Type	Journal
Year	2010
Where	JMLR
Authors	Steve Hanneke, Liu Yang

Comments (0)

Sciweavers

Negative Results for Active Learning with Convex Losses

Convex Loss Functions | JMLR 2010 | Passive Learning | Proper Active Learning |

Explore & Download

Productivity Tools

Document Tools

Image Tools

Sciweavers