Performance Guarantees for Regularized Maximum Entropy Density Estimation

We consider the problem of estimating an unknown probabilit y d stribution from samples using the principle of maximum entro py (maxent). To alleviate overfitting with a very large number of features, w e propose applying the maxent principle with relaxed constraints on the expect ations of the features. By convex duality, this turns out to be equivalent to… CONTINUE READING

5 Figures & Tables


Citations per Year

149 Citations

Semantic Scholar estimates that this publication has 149 citations based on the available data.

See our FAQ for additional information.