Negative Results for Active Learning with Convex Losses

Steve Hanneke; Liu Yang

2010 AISTATS AISTATS 2010

Negative Results for Active Learning with Convex Losses

Abstract

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.

🐣 Hot Topic Early Bird - active learning

Authors

Steve Hanneke, Liu Yang

Topics

Machine Learning > Learning Types > Active Learning Machine Learning > Optimization & Theory > Learning Theory Machine Learning > Learning Types > Supervised Learning

Keywords

active learning convex loss passive learning minimax rate proper learning

Download PDF

More from AISTATS 2010

All AISTATS 2010 papers →

Noise-contrastive estimation: A new estimation principle for unnormalized statistical models

Boosted Optimization for Network Classification

Dirichlet Process Mixtures of Generalized Linear Models

Coherent Inference on Optimal Play in Game Trees

Collaborative Filtering via Rating Concentration

Maximum-likelihood learning of cumulative distribution functions on graphs