Learning Efficient Random Maximum A-Posteriori Predictors with Non-Decomposable Loss Functions

By Tamir Hazan, Subhransu Maji, Joseph Keshet, Tommi S. Jaakkola. 2013

22 citations recorded by the source corpus.

Subfields: Probabilistic & Bayesian Methods, Statistical Learning Theory

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Probabilistic & Bayesian Methods

1. Tamir Hazan
2. Subhransu Maji
3. Tommi S. Jaakkola
4. Lise Getoor
5. Bert Huang
6. Ben London
7. David M. Blei
8. Chris J. Maddison

In Statistical Learning Theory

1. Lise Getoor
2. Tamir Hazan
3. Ben London
4. Tommi S. Jaakkola
5. Subhransu Maji
6. Bert Huang
7. Michael L. Littman
8. Csaba Szepesvari

Citations in the corpus

• On Sampling from the Gibbs Distribution with Random Maximum A-Posteriori Perturbations (2013, background): “[9, 6] consider the generalization properties of such models within PAC-Bayesian theory.”
• Stability and Generalization in Structured Prediction (2016, background): “Obtaining fully annotated examples can be time-consuming and expensive, due to the number of variables.”